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. 20-GEMMASCOPE-RES-131K
    6. 14881
    Prev
    Next
    INDEX
    Explanations

    topics related to government processes and policies

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

    academic and professional fields

    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
     OMITBAD
    -0.70
    WriteTagHelper
    -0.67
     autorytatywna
    -0.66
    aarrggbb
    -0.63
    MigrationBuilder
    -0.62
    VIAF
    -0.62
    httphttps
    -0.62
    bewerken
    -0.60
    :✨
    -0.59
    IsPostBack
    -0.59
    POSITIVE LOGITS
     العم
    0.30
     dramatique
    0.30
    HostException
    0.29
     oeuvres
    0.28
    offsetof
    0.28
    úgó
    0.27
     activities
    0.27
    yntaxException
    0.27
    velocityY
    0.26
     congé
    0.26
    Activations Density 0.201%

    No Known Activations