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. 258
    Prev
    Next
    INDEX
    Explanations

    attends to the token "into" from various 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
    0:0.06
    1:0.03
    2:0.02
    3:0.02
    4:0.03
    5:0.02
    6:0.03
    7:0.76
    Negative Logits
     an
    -0.45
     a
    -0.43
     the
    -0.36
     he
    -0.33
     lot
    -0.30
     ‘
    -0.30
     its
    -0.30
     all
    -0.30
     par
    -0.30
     half
    -0.29
    POSITIVE LOGITS
    AddTagHelper
    0.59
     صوتيه
    0.56
    TagMode
    0.54
     الحره
    0.52
    MessageOf
    0.51
     negroes
    0.50
     postIndex
    0.50
     estimés
    0.50
     Shakspeare
    0.49
    
    0.49
    Activations Density 0.349%

    No Known Activations