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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12782
    Prev
    Next
    INDEX
    Explanations

    Java and Android framework-related imports and components

    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
    ↵↵
    -0.40
     no
    -0.40
     ranging
    -0.37
     mod
    -0.35
     with
    -0.34
    <eos>
    -0.34
     simply
    -0.34
     knowing
    -0.34
    ,
    -0.34
     means
    -0.33
    POSITIVE LOGITS
     ब्रेकडाउन
    0.98
    UserScript
    0.77
     CreateTagHelper
    0.74
    ValueStyle
    0.73
    haikusbot
    0.73
    IntoConstraints
    0.71
    TagMode
    0.71
     snippetHide
    0.70
    رشف
    0.70
    InjectAttribute
    0.69
    Activations Density 0.229%

    No Known Activations