© 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. 493
    Prev
    Next
    INDEX
    Explanations

    content related to television shows and movies

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

    titles of books, films, and media publications.

    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
     препратки
    -0.60
    OGND
    -0.60
     autorytatywna
    -0.59
    +#+#
    -0.58
     مشين
    -0.56
    awtextra
    -0.54
    Бахар
    -0.54
    पया
    -0.53
    脚注の使い方
    -0.51
    
    -0.51
    POSITIVE LOGITS
     haka
    0.45
     houſe
    0.42
    Equation
    0.38
    ſelves
    0.38
    tudiant
    0.37
     itſelf
    0.36
     ſon
    0.36
     fau
    0.36
    ſelf
    0.36
    ™.
    0.36
    Activations Density 0.233%

    No Known Activations