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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 335
    Prev
    Next
    INDEX
    Explanations

    attends to redirect-related tokens from URL-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.03
    2:0.04
    3:0.06
    4:0.48
    5:0.13
    6:0.06
    7:0.06
    Negative Logits
     myſelf
    -0.34
     decât
    -0.34
     faptul
    -0.33
     îna
    -0.33
     faſt
    -0.30
    jména
    -0.30
     maaaring
    -0.29
     piú
    -0.28
    neté
    -0.28
    But
    -0.28
    POSITIVE LOGITS
    "],
    
    0.57
    ")));
    
    0.54
     GenerationType
    0.54
    UnusedPrivate
    0.53
    )))
    
    0.52
    "},
    
    0.51
    }".
    0.51
     estekak
    0.51
     tartalomajánló
    0.51
    ")]
    
    0.50
    Activations Density 0.043%

    No Known Activations