© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 407
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS markup related to web development frameworks

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    include <

    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-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
    formik
    -0.51
    FXML
    -0.50
     knex
    -0.49
     onBind
    -0.45
    knex
    -0.44
    Coy
    -0.42
    ngrx
    -0.42
    POV
    -0.42
    jshint
    -0.40
     handleSubmit
    -0.40
    POSITIVE LOGITS
    expandindo
    0.46
    hoeddwyd
    0.45
    NgModule
    0.43
    pushFollow
    0.42
     eiland
    0.40
     nécessaires
    0.40
     silnika
    0.39
     península
    0.39
     přid
    0.39
    elesen
    0.39
    Activations Density 0.326%

    No Known Activations