Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10408
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to networking protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    EndProject
    -0.63
     LEYENDO
    -0.61
     surla
    -0.58
     Réponses
    -0.58
     prédio
    -0.56
    rungsseite
    -0.56
    uttavia
    -0.53
     tempfile
    -0.52
     linho
    -0.52
     BoxFit
    -0.51
    POSITIVE LOGITS
     packet
    0.95
     packets
    0.85
     PACK
    0.81
     Packet
    0.78
     Pack
    0.78
    packet
    0.75
    Packet
    0.69
     paket
    0.69
     pack
    0.66
     flow
    0.65
    Activations Density 0.713%

    No Known Activations