© 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
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 5523
    Prev
    Next
    INDEX
    Explanations

    questions and identifiers related to technology or hardware components, especially in relation to media or audio devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]</
    -0.44
    󠁣
    -0.42
     مشين
    -0.40
     convention
    -0.39
    ]='
    -0.38
    =('
    -0.38
    ruptedException
    -0.38
    にほんブログ村
    -0.37
    EndProject
    -0.37
    =$("#
    -0.36
    POSITIVE LOGITS
    :✨
    1.19
    ✨
    0.79
    ✨:
    0.77
     ✨
    0.71
    ✨✨
    0.60
    évaluateur
    0.55
     hochzeit
    0.55
     nakalista
    0.54
    PRODUCT
    0.51
    parsedMessage
    0.49
    Activations Density 0.028%

    No Known Activations