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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3373
    Prev
    Next
    INDEX
    Explanations

    references to CSS stylesheets and links

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

    "css" and related stylesheet tokens

    np_acts-logits-general · gemini-2.0-flash

    css stylesheet links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bartholomew
    -0.47
    MongoClient
    -0.46
     MongoClient
    -0.44
    AlterField
    -0.44
    RTEX
    -0.43
    Delimited
    -0.43
    HandlerContext
    -0.43
     hecta
    -0.42
    Clik
    -0.41
     Brooke
    -0.40
    POSITIVE LOGITS
    css
    2.98
     css
    2.47
     CSS
    2.20
    CSS
    2.17
    Css
    2.08
     Css
    1.76
    scss
    1.21
     CS
    0.83
    cs
    0.83
     StyleSheet
    0.82
    Activations Density 0.057%

    No Known Activations