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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7085
    Prev
    Next
    INDEX
    Explanations

    prepositions, specifically the word "of."

    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
     purpoſe
    -0.66
     uſed
    -0.64
     pleaſure
    -0.61
     himſelf
    -0.59
     Addis
    -0.59
     poffe
    -0.59
     Cæsar
    -0.58
     écrite
    -0.58
     sphinx
    -0.58
     itſelf
    -0.56
    POSITIVE LOGITS
     OF
    1.25
    MessageOf
    1.17
    .)}
    1.15
    .}(
    1.13
     Of
    1.04
     the
    0.98
    Personendaten
    0.97
    ")));
    
    0.96
    */
    
    
    0.96
    "])
    
    0.95
    Activations Density 1.565%

    No Known Activations