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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10769
    Prev
    Next
    INDEX
    Explanations

    classes and data structures in code, particularly related to animals

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    programming and i18n

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esegu
    -0.48
     épreuve
    -0.46
     arşiv
    -0.46
    itinéraire
    -0.45
     Primaria
    -0.45
    wärts
    -0.44
     navideña
    -0.44
     isolado
    -0.44
     dependencia
    -0.44
    PostInfinity
    -0.44
    POSITIVE LOGITS
    hoeddwyd
    0.61
     listOf
    0.58
     {:.
    0.57
     kaarangay
    0.57
     newName
    0.56
     noOf
    0.55
     tartalomajánló
    0.54
     fusca
    0.54
     imageName
    0.54
     scanf
    0.53
    Activations Density 0.348%

    No Known Activations