© 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. 1-GEMMASCOPE-RES-16K
    6. 8278
    Prev
    Next
    INDEX
    Explanations

    terms associated with data storage and structural organization in computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.48
     يتيمه
    -0.48
    StructEnd
    -0.46
     proveedor
    -0.46
    
    -0.45
     fournisseur
    -0.45
    Indented
    -0.45
     Winaray
    -0.44
    RTHOOK
    -0.44
    पया
    -0.43
    POSITIVE LOGITS
     arch
    0.72
     Arch
    0.66
    arch
    0.63
     archive
    0.63
    Arch
    0.61
     intermediate
    0.59
     exchange
    0.59
    archive
    0.58
    Archive
    0.57
     ARCH
    0.57
    Activations Density 0.386%

    No Known Activations