Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 7962
    Prev
    Next
    INDEX
    Explanations

    sentences that describe collective actions or statements made by a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.88
    styleType
    -0.82
     protoimpl
    -0.77
    IndentedString
    -0.77
    DebuggerNonUser
    -0.77
    homonymie
    -0.74
    StoryboardSegue
    -0.74
    ///</
    -0.74
     comigo
    -0.72
     JOptionPane
    -0.70
    POSITIVE LOGITS
     ourselves
    1.89
     our
    1.14
     Our
    1.11
     We
    1.09
    Our
    1.04
     we
    1.03
     نحن
    0.98
    We
    0.93
     можем
    0.92
    we
    0.92
    Activations Density 0.617%

    No Known Activations