© 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. 7812
    Prev
    Next
    INDEX
    Explanations

    phrases related to limitations or inability to perform actions

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

    "You can't" or "cannot"

    np_acts-logits-general · gemini-2.0-flash

    can't/cannot followed by verb

    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
     "..\..\..\
    -0.64
    ThroughAttribute
    -0.57
    Diweddarwch
    -0.55
    AndEndTag
    -0.53
    webElementXpaths
    -0.50
     "..\..\
    -0.49
    uxxxx
    -0.49
     instead
    -0.48
     esternos
    -0.48
     piuttosto
    -0.47
    POSITIVE LOGITS
     truly
    0.85
    truly
    0.83
     meaningfully
    0.81
     realistically
    0.77
    Truly
    0.75
     hope
    0.70
     raisonnable
    0.69
     Truly
    0.69
     reliably
    0.67
     expect
    0.66
    Activations Density 0.361%

    No Known Activations