© 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. 7798
    Prev
    Next
    INDEX
    Explanations

    issues related to online information retrieval and user difficulties with documentation

    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
     istället
    -0.54
     rather
    -0.48
    而不是
    -0.47
     various
    -0.47
     plutôt
    -0.46
     piuttosto
    -0.44
     siempre
    -0.43
     myös
    -0.43
    EVERY
    -0.43
    various
    -0.42
    POSITIVE LOGITS
     neither
    2.03
    neither
    1.85
    Neither
    1.80
     Neither
    1.79
     nor
    1.58
     żad
    1.40
     tampoco
    1.40
     nenhum
    1.35
     nicio
    1.34
     nici
    1.33
    Activations Density 0.036%

    No Known Activations