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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103099
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations and endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CreateMap
    -0.42
     onPostExecute
    -0.40
    }-*/;
    -0.38
    lacable
    -0.36
     sembler
    -0.35
    UnsafeEnabled
    -0.35
    retung
    -0.34
     Previously
    -0.34
    outi
    -0.33
     تانيه
    -0.33
    POSITIVE LOGITS
     nahilalakip
    0.53
    oa̍t
    0.49
    IUrlHelper
    0.48
    Наводи
    0.44
     Majefty
    0.43
    kháu
    0.43
     Photocase
    0.42
    таратура
    0.42
    utilisons
    0.42
     pend
    0.41
    Activations Density 0.006%

    No Known Activations