© 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. 38-GEMMASCOPE-RES-16K
    11. 15920
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminologies related to computer systems and programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittarius
    -0.35
     hôtes
    -0.34
     dead
    -0.34
    AccessorTable
    -0.33
    taking
    -0.32
    hilangan
    -0.32
    alyptus
    -0.32
     stos
    -0.32
    SupportActionBar
    -0.32
     Tipps
    -0.31
    POSITIVE LOGITS
    :✨
    0.64
     AssemblyCulture
    0.62
     snippetHide
    0.55
    tvguidetime
    0.54
     يتيمه
    0.53
    ➟
    0.53
    styleType
    0.52
     transfieras
    0.52
    delwed
    0.50
    脚注の使い方
    0.49
    Activations Density 0.842%

    No Known Activations