© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11370
    Prev
    Next
    INDEX
    Explanations

    links and references to external resources, particularly URLs and supplementary materials

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

    URLs starting with "http://" or "https://"

    np_acts-logits-general · gemini-2.0-flash

    web links and resources

    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
    хьтан
    -0.70
    RenderAtEndOf
    -0.68
    Дереккөздер
    -0.67
     Offisielt
    -0.63
     dAtA
    -0.62
     themſelves
    -0.61
    TabStop
    -0.60
     AssemblyCulture
    -0.57
     FetchType
    -0.57
     geldig
    -0.56
    POSITIVE LOGITS
    enumi
    0.50
    ')],
    0.50
    ]")]
    0.49
     $<$
    0.47
    STORAGE
    0.46
    orkel
    0.46
    urlopen
    0.46
    skem
    0.45
    ığım
    0.45
    μεν
    0.44
    Activations Density 0.262%

    No Known Activations