© 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. 24-GEMMASCOPE-RES-16K
    6. 16011
    Prev
    Next
    INDEX
    Explanations

    syntax and structure of code snippets

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

    Objective-C code related to UI elements or logging

    np_acts-logits-general · gemini-2.0-flash

    objective-c code snippets

    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
    IVEREF
    -0.67
     autorytatywna
    -0.61
     саны
    -0.55
    DebuggerNonUser
    -0.55
    .".
    -0.53
     {}));
    -0.52
    ")));
    -0.52
    ());
    
    -0.51
    UnknownFieldSet
    -0.51
    "));
    
    -0.51
    POSITIVE LOGITS
     [
    1.00
    NSLog
    0.91
     ([
    0.90
    [
    0.87
     [[
    0.86
    [[
    0.85
     [_
    0.83
    [_
    0.83
    ([
    0.82
    ,[
    0.81
    Activations Density 0.028%

    No Known Activations