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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4393
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and identifiers used in code snippets

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

    before slashes, colons, underscores, or hyphens

    np_acts-logits-general · gemini-2.0-flash

    software component identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.01
     "));
    -0.93
     ?";
    -0.85
    )"),
    -0.84
     ));
    -0.84
    AddTagHelper
    -0.84
    ","");
    -0.84
    )?;
    -0.84
    protoimpl
    -0.83
     );
    
    -0.83
    POSITIVE LOGITS
    .
    1.07
    -
    0.97
    :
    0.95
    /
    0.89
    @
    0.86
    ::
    0.80
    ~
    0.77
    _
    0.75
    ://
    0.74
    #
    0.73
    Activations Density 1.276%

    No Known Activations