© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104731
    Prev
    Next
    INDEX
    Explanations

    methods or functions related to encoding data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    DeleteBehavior
    -1.20
    ThroughAttribute
    -0.85
     ControllerBase
    -0.83
    MLLoader
    -0.81
    FieldBuilder
    -0.78
     EconPapers
    -0.76
    Hentet
    -0.73
    spender
    -0.73
     BoxFit
    -0.71
    jsxFileName
    -0.71
    POSITIVE LOGITS
     LCCN
    1.41
    getDescriptor
    1.29
    encodeWith
    1.24
     titul
    0.71
     lccn
    0.62
    getExternal
    0.45
    ();*/
    0.44
    ]";
    0.42
    >--}}
    0.42
    '],$
    0.41
    Activations Density 0.000%

    No Known Activations