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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6122
    Prev
    Next
    INDEX
    Explanations

    terms related to axons and their properties in neuronal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.60
    CodeAttribute
    -0.49
    Diweddarwch
    -0.48
    jooq
    -0.47
    rungsseite
    -0.46
     gefe
    -0.44
    UserScript
    -0.44
    makeConstraints
    -0.42
    VolleyError
    -0.42
    iprot
    -0.41
    POSITIVE LOGITS
    ax
    1.34
     ax
    1.30
     Ax
    1.19
    Ax
    1.14
    AX
    1.05
     Axial
    0.99
     axial
    0.99
     AX
    0.96
     Axis
    0.96
    axial
    0.95
    Activations Density 1.308%

    No Known Activations