Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2392
    Prev
    Next
    INDEX
    Explanations

    instances or uses of the word "literally" 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 @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mayfield
    -0.65
     entanto
    -0.63
    chtung
    -0.60
    ouncil
    -0.57
    Lass
    -0.54
    isOk
    -0.54
     Moray
    -0.53
     Marqu
    -0.52
    ----------------
    -0.51
    SBATCH
    -0.51
    POSITIVE LOGITS
     literally
    1.32
    Literally
    1.29
    literally
    1.26
     Literally
    1.24
     literal
    1.18
     literalmente
    1.06
     Literal
    1.06
    literal
    1.02
    LITERAL
    0.92
     litté
    0.89
    Activations Density 0.056%

    No Known Activations