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. 22335
    Prev
    Next
    INDEX
    Explanations

    terms related to constraints and limits in measurements and relations

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

    constrain on

    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
     ProtoMessage
    -0.44
    تقاوى
    -0.43
     виправивши
    -0.42
    CardHeader
    -0.39
    цездатний
    -0.39
    dflare
    -0.38
     didReceive
    -0.37
     AppComponent
    -0.37
    StreetMap
    -0.37
    UrlResolution
    -0.37
    POSITIVE LOGITS
    Constraints
    0.64
     Constraints
    0.64
     constraint
    0.63
     constraints
    0.61
    Constraint
    0.60
     Constraint
    0.59
    constraint
    0.57
     constrain
    0.52
     restriction
    0.51
     restraints
    0.50
    Activations Density 0.166%

    No Known Activations