© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7095
    Prev
    Next
    INDEX
    Explanations

    code snippets related to repository patterns in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code repositories or repository access

    np_acts-logits-general · gemini-2.0-flash

    Generic repository

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.80
     Indra
    -0.70
     Ramb
    -0.67
     Bryce
    -0.66
    DebuggerNonUser
    -0.66
     Lyle
    -0.63
    XmlType
    -0.62
    Bryce
    -0.62
     nakalista
    -0.62
     BRON
    -0.62
    POSITIVE LOGITS
    Repository
    2.36
     Repository
    2.33
     repository
    2.23
    repository
    2.10
    getRepository
    1.93
     repo
    1.87
    repo
    1.86
    Repo
    1.79
     Repo
    1.66
     repositories
    1.66
    Activations Density 0.212%

    No Known Activations