© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 1695
    Prev
    Next
    INDEX
    Explanations

    concepts related to challenges and limitations in scientific and technological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -0.53
    tvguidetime
    -0.45
    retanto
    -0.42
     quia
    -0.42
    teilungen
    -0.40
    BASELINE
    -0.40
     Dispatch
    -0.39
    zzleHttp
    -0.39
    GIVEREF
    -0.38
     envelope
    -0.37
    POSITIVE LOGITS
    SharedDtor
    0.59
    MessageOf
    0.50
    rrggbb
    0.44
    IConfiguration
    0.44
    delwed
    0.44
    __(/*!
    0.43
     *++
    0.43
    +:+
    0.43
    存于互联网档案馆
    0.43
     nahilalakip
    0.42
    Activations Density 0.988%

    No Known Activations