© 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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15333
    Prev
    Next
    INDEX
    Explanations

    legal and licensing terms associated with software and patents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.94
     utafitiHapana
    -0.85
     AssemblyCulture
    -0.85
    IntoConstraints
    -0.82
    OGND
    -0.80
     resourceCulture
    -0.80
     メンテナ
    -0.79
    RenderAtEndOf
    -0.78
    <unused43>
    -0.75
    <pad>
    -0.75
    POSITIVE LOGITS
    formazioni
    0.28
     Greek
    0.28
    <eos>
    0.27
     
    0.27
    Dear
    0.26
     disegni
    0.25
    ***
    0.24
     Preguntas
    0.24
     Italian
    0.23
     how
    0.23
    Activations Density 3.424%

    No Known Activations