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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-ATT-16K
    6. 6420
    Prev
    Next
    INDEX
    Explanations

    attends to tokens associated with the operation "convert" from corresponding tokens related to the numeric identifier "1"

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/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.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.03
    1:0.18
    2:0.03
    3:0.03
    4:0.21
    5:0.42
    6:0.02
    7:0.03
    Negative Logits
     يتيمه
    -0.41
    UserScript
    -0.33
     فريبيس
    -0.30
    bootstrapcdn
    -0.30
     }</
    -0.30
    $
    
    -0.29
     nahilalakip
    -0.28
    abestanden
    -0.28
    ]--;
    -0.27
    tagext
    -0.27
    POSITIVE LOGITS
     StringTokenizer
    0.26
     ende
    0.25
    حوالہ
    0.25
    ANDUM
    0.25
    iotensin
    0.24
     acercarse
    0.24
     uptime
    0.24
     înd
    0.24
     defire
    0.24
     phosphory
    0.23
    Activations Density 0.380%

    No Known Activations