© 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. 8218
    Prev
    Next
    INDEX
    Explanations

    specific terms and variables related to programming or software development

    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
     OB
    -0.43
    EPIC
    -0.43
     EPIC
    -0.43
     Ep
    -0.42
     EP
    -0.42
     AV
    -0.41
    EPI
    -0.41
     EV
    -0.40
     ESC
    -0.39
    IVer
    -0.39
    POSITIVE LOGITS
     Ae
    1.35
     ae
    1.35
     AA
    1.34
    AA
    1.32
     aa
    1.28
    ae
    1.24
     AE
    1.24
    aa
    1.23
    Ae
    1.22
    ee
    1.15
    Activations Density 0.943%

    No Known Activations