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. 10-GEMMASCOPE-ATT-16K
    6. 6323
    Prev
    Next
    INDEX
    Explanations

    attends to clauses that express clarity, juxtaposing them with vague related tokens

    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
    0:0.11
    1:0.10
    2:0.12
    3:0.05
    4:0.03
    5:0.01
    6:0.07
    7:0.46
    Negative Logits
     kasarigan
    -0.57
    mybatisplus
    -0.49
    ValueStyle
    -0.48
    ########.
    -0.47
    saraba
    -0.47
    ="@+
    -0.46
    IsMutable
    -0.45
    ArrowToggle
    -0.44
    __*/
    -0.42
    verwijspagina
    -0.41
    POSITIVE LOGITS
    getLayout
    0.21
     middle
    0.20
    Kind
    0.20
     compared
    0.20
     Thousands
    0.19
     tes
    0.19
    บ้าง
    0.19
     يكن
    0.19
    jo
    0.19
    蓬
    0.19
    Activations Density 0.180%

    No Known Activations