© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15340
    Prev
    Next
    INDEX
    Explanations

    technical references and coding syntax in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ch
    -1.48
     Ch
    -1.41
    Ch
    -1.35
    CH
    -1.32
    ch
    -1.30
     CH
    -1.30
     Che
    -1.20
     Chi
    -1.20
     che
    -1.18
    Chi
    -1.18
    POSITIVE LOGITS
     lenker
    0.42
     AdapterView
    0.40
    IBOutlet
    0.38
     AssemblyCulture
    0.36
    arraycopy
    0.35
    ServletRequest
    0.33
    HasAnnotation
    0.33
    tellten
    0.32
    новништво
    0.31
     Souha
    0.31
    Activations Density 1.346%

    No Known Activations