© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7687
    Prev
    Next
    INDEX
    Explanations

    programming syntax and function calls

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

    Code snippets with "+" signs

    np_acts-logits-general · gemini-2.0-flash

    ngx subrequest handler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -1.09
    sizeCache
    -1.00
     resourceCulture
    -0.98
    SharedCtor
    -0.90
     AssemblyCompany
    -0.90
    UnusedPrivate
    -0.86
    astify
    -0.82
     Normdatei
    -0.81
    Билгалдахарш
    -0.81
     transfieras
    -0.81
    POSITIVE LOGITS
    ↵↵↵
    0.41
    ↵
    0.36
    ↵↵
    0.34
    CE
    0.33
      
    0.32
    ser
    0.32
    CS
    0.32
     ce
    0.32
    T
    0.31
    起
    0.28
    Activations Density 0.200%

    No Known Activations