© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3263
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface components and their actions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ."),
    -0.91
    ."));
    -0.85
    ?”,
    -0.83
    ?")
    -0.79
    .”)
    -0.79
    .";
    
    -0.79
    ?");
    -0.78
    ."]
    -0.77
    ?",
    -0.77
    ”),
    -0.74
    POSITIVE LOGITS
    OfWork
    0.63
     And
    0.62
    And
    0.59
    and
    0.54
    Of
    0.53
     Of
    0.53
     Wicidata
    0.53
    OfDay
    0.53
    /*
    0.52
     extends
    0.51
    Activations Density 0.574%

    No Known Activations