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. 13000
    Prev
    Next
    INDEX
    Explanations

    period punctuation in code and parameters in function definitions

    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
     instead
    -0.36
     once
    -0.35
     along
    -0.35
     broke
    -0.34
     followed
    -0.34
     to
    -0.34
     indeed
    -0.33
     should
    -0.33
     upon
    -0.33
     then
    -0.32
    POSITIVE LOGITS
    zzleHttp
    0.79
     nakalista
    0.74
    ArgsConstructor
    0.65
    Personendaten
    0.61
     vPvB
    0.61
    StructEnd
    0.60
    OGND
    0.60
    UserScript
    0.58
    adaptiveStyles
    0.57
     ProtoMessage
    0.56
    Activations Density 0.149%

    No Known Activations