© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 61452
    Prev
    Next
    INDEX
    Explanations

    programmatic aspects related to model definitions in a Django framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ::*;
    -0.40
    "]));
    -0.35
    >>;
    -0.34
    RegressionTest
    -0.34
    ⏟
    -0.33
     }}">
    -0.33
     Hofmann
    -0.32
     }));
    -0.31
    })->
    -0.31
    /$',
    -0.31
    POSITIVE LOGITS
    NameInMap
    0.76
    rungsseite
    0.73
    ReusableCell
    0.68
    NOPQRST
    0.64
    GOTREF
    0.61
     disponibilités
    0.59
    tagHelper
    0.59
    protoc
    0.58
    Билгалдахарш
    0.57
     TType
    0.57
    Activations Density 0.000%

    No Known Activations