© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 14479
    Prev
    Next
    INDEX
    Explanations

    references to arrays and their manipulations

    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
     Vina
    -0.75
    eseorang
    -0.75
    IndentedString
    -0.72
     rosse
    -0.72
    }))
    
    -0.71
    umenten
    -0.70
     giacca
    -0.69
    Bism
    -0.68
    Gust
    -0.68
    uminescence
    -0.67
    POSITIVE LOGITS
     arrays
    1.63
    arrays
    1.56
     Array
    1.53
     array
    1.52
    array
    1.49
    ARRAY
    1.47
     ARRAY
    1.41
    Array
    1.39
     Arrays
    1.31
    isArray
    1.20
    Activations Density 0.101%

    No Known Activations