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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6980
    Prev
    Next
    INDEX
    Explanations

    proper nouns and significant titles or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Suara
    -0.64
    Personensuche
    -0.63
    contentLoaded
    -0.61
    ativement
    -0.60
     Вікі
    -0.58
     Audiodateien
    -0.57
    IContainer
    -0.57
    ">//
    -0.55
     AssemblyCulture
    -0.53
     RSSSF
    -0.51
    POSITIVE LOGITS
    Enllaços
    0.86
    مصادر
    0.76
    KommentareTeilen
    0.63
    Filmografia
    0.62
     -,
    0.58
    VolleyError
    0.57
     lenker
    0.57
     SwiftUI
    0.55
    ubscribe
    0.53
     joaat
    0.53
    Activations Density 0.556%

    No Known Activations