© 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 EvalsExportsinterp-engineNEWAPI 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. 12062
    Prev
    Next
    INDEX
    Explanations

    phrasings related to overall assessments and evaluations of different situations or subjects

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

    "Across" followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    across broadly

    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
     ſtate
    -0.77
     raiſ
    -0.71
     uſed
    -0.68
    ArgsConstructor
    -0.67
     leaſt
    -0.67
     reaſon
    -0.67
     ſame
    -0.66
     fhew
    -0.66
     beſt
    -0.66
     diſt
    -0.66
    POSITIVE LOGITS
     overall
    1.19
    overall
    1.06
     Overall
    0.93
     across
    0.93
    Overall
    0.92
    全体的に
    0.89
     all
    0.86
     everywhere
    0.86
    everywhere
    0.81
     overal
    0.77
    Activations Density 0.112%

    No Known Activations