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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2641
    Prev
    Next
    INDEX
    Explanations

    specific journal article citation formats and structures

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

    citations and references in academic and legal documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    |()
    -0.47
     Vance
    -0.47
    nonumber
    -0.45
     canada
    -0.45
    keyCode
    -0.45
    uVar
    -0.45
     vergeben
    -0.44
    volt
    -0.43
    sistor
    -0.42
     NOVA
    -0.42
    POSITIVE LOGITS
    Chham
    0.70
    Ch
    0.58
     disambiguazione
    0.58
     chave
    0.58
     CHURCH
    0.57
    MessageTagHelper
    0.57
     Ch
    0.57
    ch
    0.56
     chaves
    0.54
     flecha
    0.53
    Activations Density 0.413%

    No Known Activations