© 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. 1304
    Prev
    Next
    INDEX
    Explanations

    key details about individuals and their relationships in a biographical context

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

    conjunctions and connective words that link two entities or clauses together.

    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
    ſon
    -0.39
     Sora
    -0.38
     MenuView
    -0.38
    WebServlet
    -0.38
    分別
    -0.37
    乏
    -0.37
    verton
    -0.36
    殊
    -0.36
    RUnlock
    -0.36
     Pd
    -0.36
    POSITIVE LOGITS
    兩人
    1.22
    两人
    1.19
     duo
    1.13
     pair
    1.09
     keduanya
    0.96
    两人的
    0.94
    二人
    0.92
    两者
    0.92
     couple
    0.83
     beiden
    0.81
    Activations Density 0.314%

    No Known Activations