© 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. 7-GEMMASCOPE-RES-16K
    11. 13605
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions related to creation, evaluation, and significant accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.61
     ſche
    -0.58
     ſtate
    -0.57
     pleaſure
    -0.56
    ſelf
    -0.54
     Riproduzione
    -0.52
     fhew
    -0.51
     vérit
    -0.50
    fören
    -0.49
     Houſe
    -0.47
    POSITIVE LOGITS
    eeded
    0.69
    tened
    0.69
    ened
    0.68
    aced
    0.65
    tered
    0.65
    ourced
    0.63
    mped
    0.63
    utched
    0.63
    LETED
    0.63
    essed
    0.62
    Activations Density 0.747%

    No Known Activations