© 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. 10092
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and data functions

    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
     avoient
    -1.26
     auroit
    -1.22
     eût
    -1.15
     feroit
    -1.13
     fédé
    -1.09
     ferons
    -1.09
     miniaturka
    -1.08
     coû
    -1.08
     recev
    -1.05
     morrer
    -1.04
    POSITIVE LOGITS
     pod
    0.65
     od
    0.61
     wy
    0.60
     w
    0.59
     na
    0.57
     nie
    0.55
     „
    0.52
     z
    0.52
     za
    0.52
     lub
    0.50
    Activations Density 0.081%

    No Known Activations