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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 8196
    Prev
    Next
    INDEX
    Explanations

    specific interactions and relationships in various contexts

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

    Followed by a colon or comma

    np_acts-logits-general · gemini-2.0-flash

    in action

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    })->
    -0.59
    queryInterface
    -0.55
     RIPRODUZIONE
    -0.45
    })*/
    -0.43
     enfans
    -0.40
     vPvB
    -0.40
    ]){
    
    -0.39
    )=>{
    
    -0.38
    LLocation
    -0.38
    }?>
    -0.38
    POSITIVE LOGITS
    omitempty
    0.66
    PerformLayout
    0.62
    ChildScrollView
    0.56
    VersionUID
    0.55
     elsewhere
    0.54
    PerPage
    0.53
    lause
    0.53
    幄
    0.53
    ToAction
    0.51
     onOptions
    0.51
    Activations Density 0.863%

    No Known Activations