© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 39192
    Prev
    Next
    INDEX
    Explanations

    connections and relationships in sentences, particularly involving conjunctions and references to subjects and their actions

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

    anything in between

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     AssemblyVersion
    -0.52
    IVEREF
    -0.50
     folgender
    -0.43
    Билгалдахарш
    -0.43
    }*/
    
    -0.42
     frequência
    -0.41
    \{\\
    -0.40
     useAppContext
    -0.40
    astify
    -0.40
    HtmlAttribute
    -0.40
    POSITIVE LOGITS
    ...
    0.79
    …
    0.79
    ....
    0.76
    ….
    0.74
    .....
    0.71
     …
    0.70
    …..
    0.70
     ...
    0.70
    .......
    0.69
    ……
    0.69
    Activations Density 0.044%

    No Known Activations