© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 7745
    Prev
    Next
    INDEX
    Explanations

    terms related to neurobiology and neurotransmitter systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.34
    RestTemplate
    -0.33
     professionisti
    -0.30
    İstinadlar
    -0.30
     physis
    -0.29
     canton
    -0.29
     neutrals
    -0.29
     simples
    -0.28
     visuelle
    -0.28
    Manbalar
    -0.28
    POSITIVE LOGITS
    ilistic
    0.89
    orithmic
    0.84
    atorial
    0.83
    omeric
    0.80
    neurial
    0.80
    sonian
    0.79
    sianic
    0.79
    isional
    0.78
    izational
    0.76
    osomal
    0.76
    Activations Density 1.049%

    No Known Activations