© 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 - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 16188
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Sam" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,:);
    -0.75
    ]]);
    -0.74
     itſelf
    -0.74
     >=",
    -0.68
    liosis
    -0.67
     initComponents
    -0.65
    ]})
    -0.65
    Revis
    -0.65
     ―――――
    -0.64
     ――――――――
    -0.64
    POSITIVE LOGITS
     Sam
    0.96
    Sam
    0.90
     sam
    0.89
    sam
    0.76
     SAM
    0.75
    SAM
    0.69
    Sams
    0.63
     Sams
    0.61
     sams
    0.58
    trum
    0.56
    Activations Density 0.056%

    No Known Activations