© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 117126
    Prev
    Next
    INDEX
    Explanations

    terms related to traditional methods and their inadequacies in contemporary contexts, particularly in technology and methodology discussions

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

    methods and applicability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Besch
    -0.47
     Proof
    -0.38
    aniem
    -0.36
    🇶
    -0.36
    ムー
    -0.35
     Besch
    -0.34
     besch
    -0.32
     drink
    -0.31
     vastaan
    -0.31
    Load
    -0.31
    POSITIVE LOGITS
    rungsseite
    0.72
     ProtoMessage
    0.66
    EDEFAULT
    0.64
     ब्रेकडाउन
    0.64
    لينكات
    0.64
    EndGlobalSection
    0.64
     autorytatywna
    0.63
    AccessorTable
    0.63
    tagHelperRunner
    0.63
    esModule
    0.57
    Activations Density 0.105%

    No Known Activations