© 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. 24-GEMMASCOPE-RES-16K
    11. 12618
    Prev
    Next
    INDEX
    Explanations

    devices and their uses in various contexts

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

    Followed by "used", "found", or "typically"

    np_acts-logits-general · gemini-2.0-flash

    describing typical usage or function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Serving
    -0.61
    Externé
    -0.61
    serving
    -0.56
     đời
    -0.55
     Containing
    -0.55
    MINE
    -0.55
    lossene
    -0.53
     serving
    -0.52
    ::_('
    -0.52
    provoking
    -0.51
    POSITIVE LOGITS
     especially
    0.76
     similar
    0.75
     usually
    0.73
     characterized
    0.69
     typically
    0.69
     particularly
    0.68
     generally
    0.67
    principalColumn
    0.67
    Similar
    0.66
    NewUrlParser
    0.64
    Activations Density 0.511%

    No Known Activations