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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1371
    Prev
    Next
    INDEX
    Explanations

    attends to patients from the corresponding group of individuals who exhibit a certain characteristic or condition

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.05
    1:0.02
    2:0.04
    3:0.04
    4:0.00
    5:0.02
    6:0.05
    7:0.10
    8:0.02
    9:0.02
    10:0.01
    11:0.01
    12:0.02
    13:0.35
    14:0.15
    15:0.02
    Negative Logits
     Dad
    -0.35
     direct
    -0.35
     c
    -0.34
     dad
    -0.34
     FIL
    -0.33
     conc
    -0.33
     the
    -0.33
     Mr
    -0.33
     cons
    -0.32
     care
    -0.32
    POSITIVE LOGITS
     ainfi
    0.53
     zijne
    0.47
    ſelves
    0.46
     feroit
    0.46
     desmotivaciones
    0.43
     Italij
    0.43
     plufieurs
    0.42
     étoient
    0.42
     Económica
    0.42
     mijne
    0.41
    Activations Density 0.437%

    No Known Activations