© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5443
    Prev
    Next
    INDEX
    Explanations

    Python scripting structure, particularly the main entry point check in code

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

    Code snippets or programming questions

    np_acts-logits-general · gemini-2.0-flash

    programming and technical questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.60
    |}{$
    -0.54
    Cyfeiriadau
    -0.52
     وتسجيلات
    -0.52
     useRef
    -0.49
    ²/
    -0.48
    Autoritní
    -0.48
    原始内容存档于
    -0.47
     mapStateToProps
    -0.47
    rostis
    -0.45
    POSITIVE LOGITS
    __':
    0.91
    __":
    0.85
    __':
    0.82
    __":
    0.78
    principalTable
    0.71
    로그램
    0.70
    ContentLoaded
    0.61
     ExecuteAsync
    0.58
    Hochspringen
    0.58
     AssemblyTitle
    0.57
    Activations Density 0.031%

    No Known Activations