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. 20-GEMMASCOPE-RES-131K
    6. 13982
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to authority and responsibilities in a judicial context

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

    purpose and specific contexts

    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
     su
    -0.39
    TX
    -0.38
     horribly
    -0.36
     bad
    -0.36
     Rueda
    -0.36
     us
    -0.36
     Busse
    -0.36
    μμα
    -0.35
     beant
    -0.35
    変
    -0.35
    POSITIVE LOGITS
    MigrationBuilder
    0.77
     BorderSide
    0.59
     Савезне
    0.59
    enumi
    0.56
    URLException
    0.55
    WriteTagHelper
    0.53
     ſind
    0.53
    EFIAPI
    0.52
     estekak
    0.51
    endphp
    0.50
    Activations Density 0.148%

    No Known Activations