© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4070
    Prev
    Next
    INDEX
    Explanations

    string components related to the structure and function of data

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

    Strings in code or configuration files

    np_acts-logits-general · gemini-2.0-flash

    resource strings

    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
    Tikang
    -1.07
    tagHelperRunner
    -0.82
    InitVars
    -0.69
    +:+
    -0.69
     ويكيپيديا
    -0.66
    يكب
    -0.66
     nahilalakip
    -0.65
    NameInMap
    -0.64
    AsUp
    -0.63
    emlrt
    -0.62
    POSITIVE LOGITS
    ation
    0.55
    KommentareTeilen
    0.53
    äfts
    0.49
    ization
    0.48
     Ammon
    0.47
    ванию
    0.46
     arşivlendi
    0.45
    AMAZ
    0.44
    zene
    0.43
    ATION
    0.43
    Activations Density 0.057%

    No Known Activations