© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 12525
    Prev
    Next
    INDEX
    Explanations

    phrases communicating a sense of helplessness or feeling stuck

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

    "Cannot help but" construction

    np_acts-logits-general · gemini-2.0-flash

    cannot help but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}"></
    -0.65
     Nach
    -0.56
    parsedMessage
    -0.55
    ;}
    -0.52
    Jeografia
    -0.51
    ;"></
    -0.51
    LookAnd
    -0.51
    principalTable
    -0.49
     "{}
    -0.48
     Winaray
    -0.47
    POSITIVE LOGITS
     resist
    0.82
     temptation
    0.78
     AssemblyCulture
    0.74
    下载附件
    0.70
    empêcher
    0.69
     inescapable
    0.69
     unavoidable
    0.69
    不住
    0.66
     irresistible
    0.65
    忍不住
    0.65
    Activations Density 0.131%

    No Known Activations