© 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. 13936
    Prev
    Next
    INDEX
    Explanations

    structured formats in text, such as references to documents or code

    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
     defaultstate
    -0.43
    #
    -0.42
    resave
    -0.39
     jLabel
    -0.38
     beginnetje
    -0.37
     MainAxisSize
    -0.37
    __':
    -0.36
    ForTesting
    -0.36
    andReturn
    -0.35
    .*")]
    -0.34
    POSITIVE LOGITS
     anún
    0.51
     $_(
    0.50
    asiswa
    0.49
     '{@
    0.48
    Crossref
    0.47
     Chem
    0.46
    figer
    0.46
    Chem
    0.44
     tenisky
    0.44
     Houſe
    0.43
    Activations Density 1.543%

    No Known Activations