© 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. 2481
    Prev
    Next
    INDEX
    Explanations

    specific programming-related keywords and structures in code or markup

    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
     avoient
    -1.36
     auroit
    -1.31
     feroit
    -1.24
     eût
    -1.18
     étoit
    -1.12
     fédé
    -1.08
     pouvoit
    -1.08
    ésult
    -1.08
     étoient
    -1.07
     ferons
    -1.06
    POSITIVE LOGITS
     pod
    0.69
     w
    0.68
     od
    0.65
     wy
    0.63
     na
    0.60
     z
    0.59
     po
    0.59
     „
    0.59
     ze
    0.59
     lub
    0.57
    Activations Density 0.107%

    No Known Activations