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. 10-GEMMASCOPE-RES-16K
    6. 11625
    Prev
    Next
    INDEX
    Explanations

    details related to firearms and their components

    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
     hi
    -0.41
     Ker
    -0.40
     certified
    -0.36
     Hey
    -0.35
     dual
    -0.34
     his
    -0.34
     cues
    -0.34
     Quinn
    -0.33
     potential
    -0.33
     trained
    -0.33
    POSITIVE LOGITS
    存于互联网档案馆
    0.63
    GEBURTSDATUM
    0.63
     nahilalakip
    0.58
    featureID
    0.57
     estekak
    0.54
     zoude
    0.52
     titolata
    0.52
     pageContext
    0.52
    RTLU
    0.51
    Espèce
    0.50
    Activations Density 0.310%

    No Known Activations