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. 21-GEMMASCOPE-RES-16K
    6. 13971
    Prev
    Next
    INDEX
    Explanations

    references to the word "brown" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.58
    Ciri
    -0.58
    }*/
    
    -0.55
     }?>
    -0.55
    Lähteet
    -0.54
    первых
    -0.54
     Numerade
    -0.54
     חיצוניים
    -0.53
    damente
    -0.53
    !")
    
    -0.51
    POSITIVE LOGITS
     Browns
    0.84
    lee
    0.72
    Brow
    0.69
    BROWN
    0.67
     Sugar
    0.65
     Brown
    0.64
    Sugar
    0.63
     browns
    0.63
    JNIEnv
    0.62
     BROWN
    0.61
    Activations Density 0.102%

    No Known Activations