© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 2938
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical relationships and comparisons among values

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

    magnitude, range, and comparison

    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
     Infórmanos
    -0.61
    ſelves
    -0.60
    bootstrapcdn
    -0.60
    évaluateur
    -0.59
     <>",
    -0.59
    ſelf
    -0.57
    Diweddarwch
    -0.56
    WriteTagHelper
    -0.56
    цездатний
    -0.54
     GenerationType
    -0.53
    POSITIVE LOGITS
    getColumnIndex
    0.43
    providedIn
    0.36
    printStackTrace
    0.33
     
    0.32
     $\
    0.31
     d
    0.30
    ftc
    0.30
     major
    0.30
     ligiloj
    0.29
    Ĝ
    0.29
    Activations Density 0.163%

    No Known Activations