© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 5051
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions, particularly "and."

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

    the word "and" connecting two people or entities in a relationship context.

    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
    pecabe
    -0.64
    Чыганаклар
    -0.58
    يميديا
    -0.55
    secta
    -0.54
     indígen
    -0.54
    Билгалдахарш
    -0.53
     pinulongan
    -0.53
     amortecedor
    -0.53
     SwitchCompat
    -0.53
     contrário
    -0.52
    POSITIVE LOGITS
     others
    0.94
    others
    0.80
     Others
    0.71
    Others
    0.67
     his
    0.67
     colleagues
    0.65
     OTHERS
    0.59
     crew
    0.53
     anderen
    0.52
     cohorts
    0.49
    Activations Density 0.361%

    No Known Activations