© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 46803
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structure

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

    Constructor for DLMLifecyclePolicySchedule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ListComponent
    -0.35
     
    -0.27
    要
    -0.26
    ChildScrollView
    -0.25
    xampp
    -0.25
     os
    -0.25
     naturellement
    -0.24
     loosely
    -0.24
    date
    -0.23
     verlieren
    -0.23
    POSITIVE LOGITS
    bootstrapcdn
    0.81
    httphttps
    0.68
    KommentareTeilen
    0.66
     témoig
    0.65
     Verſ
    0.65
    
    0.62
     fashiola
    0.61
     increí
    0.61
     queſta
    0.60
     dieſe
    0.60
    Activations Density 0.024%

    No Known Activations