© 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. 7739
    Prev
    Next
    INDEX
    Explanations

    elements related to product specifications and features

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

    "included" or tokens after it

    np_acts-logits-general · gemini-2.0-flash

    included or not included

    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
    extAlignment
    -0.79
    λευτα
    -0.73
    :]:
    -0.73
     typelib
    -0.72
     Signalez
    -0.72
    SharedCtor
    -0.66
     disambiguazione
    -0.66
     MainAxisSize
    -0.64
    SharedDtor
    -0.63
     raiſ
    -0.62
    POSITIVE LOGITS
     included
    2.38
    included
    2.14
     Included
    2.07
    Included
    2.04
     INCLUDED
    1.87
    INCLUDED
    1.51
     inclusion
    1.51
     incluse
    1.50
     inclus
    1.47
     incluido
    1.44
    Activations Density 0.355%

    No Known Activations