© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105616
    Prev
    Next
    INDEX
    Explanations

    sections related to film awards and categories

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

    Empty line breaks or white space between content sections, often appearing at transition points between different document parts like categories, sections, or elements in structured documents.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    værende
    -0.45
    ніципалі
    -0.45
    RegressionTest
    -0.45
     CreateTagHelper
    -0.41
    municipi
    -0.40
    ValueStyle
    -0.38
     cuad
    -0.38
    Enllaços
    -0.38
    duled
    -0.37
     normaux
    -0.36
    POSITIVE LOGITS
     kasarigan
    0.56
     Waray
    0.53
    .*")]
    0.53
     GoogleFonts
    0.43
     SEDS
    0.42
     comps
    0.40
     Weeknd
    0.40
    ABUL
    0.39
     StatelessWidget
    0.39
     Bunny
    0.39
    Activations Density 0.024%

    No Known Activations