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. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 6186
    Prev
    Next
    INDEX
    Explanations

    attends to subsection tokens from preceding numeral or variable tokens in mathematical contexts

    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
    0:0.29
    1:0.05
    2:0.02
    3:0.04
    4:0.46
    5:0.04
    6:0.05
    7:0.02
    Negative Logits
     CURIAM
    -0.53
     doInBackground
    -0.50
     незавершена
    -0.47
     }}"></
    -0.47
    SuppressMessage
    -0.46
     HasFactory
    -0.44
     onCreateView
    -0.41
    rawDesc
    -0.41
    tvguidetime
    -0.41
    Portale
    -0.41
    POSITIVE LOGITS
     side
    0.37
     were
    0.29
    drucks
    0.28
     out
    0.27
    ebrow
    0.27
     not
    0.27
     book
    0.27
    ὐ
    0.26
     he
    0.26
     well
    0.25
    Activations Density 0.007%

    No Known Activations