© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13324
    Prev
    Next
    INDEX
    Explanations

    words related to credibility and classification of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "Creosote" (and its variations/misspellings).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    the letter sequence "Cre" at the beginning of words (particularly proper nouns and technical terms like "Creedy," "Credibility," "Creosote," "Crevasse," and "Cremeo").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    words beginning with the “cre-” (and more generally “cr-”) letter sequence.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.66
    sidemargin
    -0.55
     برانيه
    -0.53
    $_['
    -0.51
    styleUrls
    -0.50
     Wiktionnaire
    -0.47
    WebServlet
    -0.46
    []):
    -0.45
     فريبيس
    -0.45
     szóci
    -0.45
    POSITIVE LOGITS
     cre
    0.82
     Cre
    0.80
    Cre
    0.77
    cre
    0.75
     CRE
    0.68
     CRED
    0.66
     Cred
    0.60
    CRE
    0.57
    cred
    0.56
     cred
    0.53
    Activations Density 0.154%

    No Known Activations