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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15915
    Prev
    Next
    INDEX
    Explanations

    contextual references to familiarity and local relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    EndInit
    -0.43
    LookAnd
    -0.41
    templateUrl
    -0.40
    interopRequire
    -0.38
     <<<<<<<<<<<<<<
    -0.38
    WebControls
    -0.37
    起了
    -0.36
    findElement
    -0.35
     Audiodateien
    -0.35
    وردار
    -0.35
    POSITIVE LOGITS
    ⓧ
    0.59
     friendships
    0.50
     regulars
    0.50
     fréqu
    0.46
     Öffnungszeiten
    0.44
     clientèle
    0.42
     everybody
    0.42
     attendance
    0.42
     Logout
    0.42
    everybody
    0.41
    Activations Density 0.132%

    No Known Activations