© 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. 31-GEMMASCOPE-RES-16K
    11. 3484
    Prev
    Next
    INDEX
    Explanations

    elements related to iconic characters and their attributes in entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases related to formal or distinctive clothing and fashion styles.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rådet
    -0.39
    httphttps
    -0.35
    графії
    -0.35
     dolayı
    -0.33
     umane
    -0.32
    ATTN
    -0.31
    enação
    -0.30
     soltanto
    -0.30
    HS
    -0.30
     cây
    -0.30
    POSITIVE LOGITS
     style
    1.55
    like
    1.48
    esque
    1.35
    style
    1.32
    LIKE
    1.17
     type
    1.15
     estilo
    1.15
     styled
    1.12
    般的
    1.10
     STYLE
    1.09
    Activations Density 0.872%

    No Known Activations