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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7198
    Prev
    Next
    INDEX
    Explanations

    specific references to confidence intervals and statistical terms related to research or data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.50
     Lokales
    -0.50
    тябрь
    -0.44
    Geplaatst
    -0.43
    ulmuş
    -0.43
    Protos
    -0.43
    Lähteet
    -0.42
    Kariera
    -0.40
    oara
    -0.40
    DOCTYPE
    -0.40
    POSITIVE LOGITS
     Ci
    0.59
     ci
    0.58
    Cis
    0.51
     CIP
    0.50
    Ci
    0.50
     Cit
    0.50
    ci
    0.48
     Cis
    0.48
    Cit
    0.46
     CI
    0.45
    Activations Density 0.244%

    No Known Activations