© 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. 39-GEMMASCOPE-RES-16K
    11. 3266
    Prev
    Next
    INDEX
    Explanations

    biographical details about individuals, particularly related to their birthdate and place of origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTCF
    -0.50
    enderror
    -0.43
    Carriera
    -0.41
    rrggbb
    -0.39
    ">//
    -0.38
     تعدى
    -0.38
    httphttps
    -0.38
    SharedCtor
    -0.38
     nghiệp
    -0.37
     requestCode
    -0.36
    POSITIVE LOGITS
     Zac
    0.56
     Roskov
    0.51
    Zac
    0.47
    EDOM
    0.46
     ModelExpression
    0.46
     Meksiku
    0.45
     Bona
    0.45
     Colombia
    0.45
     Columbia
    0.45
     Lina
    0.44
    Activations Density 0.398%

    No Known Activations