© 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. 9-GEMMASCOPE-RES-131K
    11. 82648
    Prev
    Next
    INDEX
    Explanations

    references to entities or individuals associated with certain actions or characteristics

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

    the only [noun] that/who [verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mí
    -0.37
    SourceChecksum
    -0.36
    存于互联网档案馆
    -0.34
     لتح
    -0.33
     Mil
    -0.32
    tituzione
    -0.31
     hvilket
    -0.31
    너
    -0.31
    arakhand
    -0.30
    无
    -0.30
    POSITIVE LOGITS
    NameInMap
    0.59
    msgTypes
    0.59
    parsedMessage
    0.57
     resourceCulture
    0.56
    ScopeManager
    0.55
    AddTagHelper
    0.55
    zzleHttp
    0.54
    OGND
    0.54
    tvguidetime
    0.54
    KommentareTeilen
    0.54
    Activations Density 0.036%

    No Known Activations