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. 1215
    Prev
    Next
    INDEX
    Explanations

    attends to singular possessive forms of "manager" from corresponding plural possessive forms

    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
    2:0.08
    3:0.04
    4:0.01
    5:0.01
    6:0.03
    7:0.04
    8:0.01
    9:0.02
    10:0.02
    11:0.01
    12:0.05
    13:0.50
    14:0.07
    15:0.01
    Negative Logits
     MUD
    -0.69
     Fli
    -0.69
    noc
    -0.68
    pend
    -0.68
     Tart
    -0.68
     MIM
    -0.68
     Curs
    -0.67
     Pulsar
    -0.67
     Nub
    -0.67
    pig
    -0.67
    POSITIVE LOGITS
     venganza
    0.53
     Menschheit
    0.52
     asamblea
    0.51
     burbujas
    0.51
     juventud
    0.50
     Económica
    0.50
     civilización
    0.50
     oscuridad
    0.50
     esclavos
    0.50
     estatua
    0.49
    Activations Density 0.757%

    No Known Activations