Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13120
    Prev
    Next
    INDEX
    Explanations

    mentions of fandom and dedication to specific artists or interests

    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
    WebControls
    -0.53
    enterOuterAlt
    -0.51
     noDo
    -0.51
    IVEREF
    -0.47
    kulum
    -0.46
     дописавши
    -0.43
     <>",
    -0.42
     resourceCulture
    -0.39
    arraycopy
    -0.39
    farwydd
    -0.38
    POSITIVE LOGITS
     fans
    3.52
     fan
    3.28
     Fans
    2.98
    fans
    2.88
    Fans
    2.81
    fan
    2.56
     Fan
    2.52
    Fan
    2.47
     fãs
    2.27
    ファン
    2.25
    Activations Density 0.431%

    No Known Activations