© 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. 18-GEMMASCOPE-RES-16K
    6. 13913
    Prev
    Next
    INDEX
    Explanations

    the word "Ham" and its variations in different contexts

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

    "Ham" or "Hammett"

    np_acts-logits-general · gemini-2.0-flash

    words starting with ham

    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
    __':
    
    -0.78
     only
    -0.73
    Cyfeiriadau
    -0.63
    only
    -0.61
    )++;
    -0.60
    impresa
    -0.59
    ßerdem
    -0.58
    hru
    -0.58
    ghts
    -0.57
    Fiche
    -0.57
    POSITIVE LOGITS
     Ham
    1.02
    Ham
    0.97
     ham
    0.77
     HAM
    0.73
    ########.
    0.66
    :✨
    0.65
    #+#
    0.58
     hamster
    0.58
     Hamlet
    0.57
     Hammers
    0.57
    Activations Density 0.091%

    No Known Activations