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. 1367
    Prev
    Next
    INDEX
    Explanations

    attends to the action of destroying or abolishing associated with corresponding numerical tokens

    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
    0:0.01
    1:0.01
    2:0.02
    3:0.03
    4:0.00
    5:0.00
    6:0.09
    7:0.08
    8:0.01
    9:0.01
    10:0.01
    11:0.00
    12:0.01
    13:0.11
    14:0.49
    15:0.02
    Negative Logits
    kháu
    -0.26
     creciendo
    -0.24
     telinga
    -0.22
     plateado
    -0.21
     prohibido
    -0.21
     salvaje
    -0.21
     kelahiran
    -0.21
     plegable
    -0.21
     hembra
    -0.21
     vuestro
    -0.21
    POSITIVE LOGITS
     ſind
    0.46
     BoxFit
    0.44
    KEYCODE
    0.43
    RegressionTest
    0.42
    GraphicsUnit
    0.42
     compas
    0.40
     exc
    0.40
     cade
    0.40
     PPS
    0.39
     conval
    0.39
    Activations Density 1.054%

    No Known Activations