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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 103673
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and keywords related to the Navajo culture

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

    background repeat, package, pneumoniae

    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
     GenerationType
    -0.59
     waard
    -0.49
    BASEPATH
    -0.49
    ⟬
    -0.46
    matchCondition
    -0.45
    AppMethodBeat
    -0.45
    affiliate
    -0.45
    DidLoad
    -0.45
     doPost
    -0.45
     tolua
    -0.45
    POSITIVE LOGITS
     henvisninger
    0.60
    RegistryLite
    0.57
    utto
    0.48
    DateFormatter
    0.44
    asian
    0.41
    nextSibling
    0.41
    vscode
    0.40
    dsi
    0.39
    basicConfig
    0.39
    banez
    0.39
    Activations Density 0.006%

    No Known Activations