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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27440
    Prev
    Next
    INDEX
    Explanations

    references to belief or credibility linked to specific individuals or claims

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

    cre, pla, gre prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.70
    ########.
    -0.70
     برانيه
    -0.69
     Rohr
    -0.68
    >::
    -0.67
    ‪
    -0.67
    OwnProperty
    -0.66
     propOrder
    -0.66
    Hubert
    -0.65
     Hubert
    -0.64
    POSITIVE LOGITS
    Cre
    1.06
     Cre
    0.94
     cre
    0.88
    Gre
    0.86
    úsqueda
    0.80
     Esmeralda
    0.78
    gre
    0.75
    Ju
    0.73
     Greta
    0.73
     Pla
    0.72
    Activations Density 0.025%

    No Known Activations