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. 4252
    Prev
    Next
    INDEX
    Explanations

    classes and data types in programming context

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

    Java class declarations

    np_acts-logits-general · gemini-2.0-flash

    class inheritance and implementation

    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
    ]."
    -1.12
    )."
    -1.07
    ?".
    -1.05
    .");
    -1.04
    .";
    -1.03
    .",
    -1.03
    ."
    -1.02
    ."),
    -1.02
    ?",
    -1.02
    ?).
    -1.01
    POSITIVE LOGITS
     extends
    1.81
     implements
    1.22
     {
    1.11
     extend
    0.94
    extends
    0.93
     {
    
    0.91
     extending
    0.86
     <
    0.83
     Extend
    0.76
     inherits
    0.75
    Activations Density 0.082%

    No Known Activations