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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45468
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to statistical methods and academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     CreateTagHelper
    -0.69
     Wikimedijinoj
    -0.68
     betweenstory
    -0.67
    windowFixed
    -0.63
    KommentareTeilen
    -0.63
    #+#
    -0.61
     ComVisible
    -0.61
    MigrationBuilder
    -0.58
    wiſe
    -0.56
     gynhyrchwyd
    -0.54
    POSITIVE LOGITS
    PerformLayout
    0.45
     تضيفلها
    0.41
    RenderAtEndOf
    0.39
    ScopeManager
    0.38
    ↵
    0.35
    volmente
    0.34
     TRIAL
    0.33
    ensement
    0.33
     INCORPOR
    0.32
    bcryptjs
    0.31
    Activations Density 0.005%

    No Known Activations