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. 1198
    Prev
    Next
    INDEX
    Explanations

    attends to the term "fish" in various contexts from related terms that provide specific characteristics or types of fish

    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
    0:0.02
    1:0.02
    2:0.54
    3:0.04
    4:0.01
    5:0.01
    6:0.04
    7:0.04
    8:0.01
    9:0.01
    10:0.00
    11:0.00
    12:0.01
    13:0.12
    14:0.07
    15:0.00
    Negative Logits
    rob
    -0.46
    aked
    -0.44
    aps
    -0.42
    ered
    -0.42
    enos
    -0.42
    odor
    -0.42
    ared
    -0.41
    apro
    -0.41
    arie
    -0.41
    aura
    -0.41
    POSITIVE LOGITS
     ainfi
    0.27
     dignité
    0.27
     Infór
    0.25
     civilización
    0.24
     démocratie
    0.23
     feroit
    0.23
     capitán
    0.23
    })*/
    0.22
     autorité
    0.21
     vacuna
    0.21
    Activations Density 0.022%

    No Known Activations