Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 124978
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming and module-related terminology

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

    angular module, Trust, toggle, usp url param

    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
     AssemblyVersion
    -0.64
    bewerken
    -0.53
    Personensuche
    -0.52
     виправивши
    -0.48
     igenom
    -0.45
     Biôgrafia
    -0.44
     VIAF
    -0.43
    IsPostBack
    -0.42
     вікісторінку
    -0.42
    tagext
    -0.42
    POSITIVE LOGITS
    Kaynakça
    0.67
    BAI
    0.59
    KommentareTeilen
    0.51
    arding
    0.51
    atche
    0.47
    centerTitle
    0.45
    ngdoc
    0.41
    FailureListener
    0.41
    الحياه
    0.40
     jadx
    0.40
    Activations Density 0.002%

    No Known Activations