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. 1231
    Prev
    Next
    INDEX
    Explanations

    attends to the concept of "more" from various tokens related to quantity or increase

    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
    2:0.03
    3:0.02
    4:0.00
    5:0.01
    6:0.08
    7:0.11
    8:0.01
    9:0.01
    10:0.00
    11:0.01
    12:0.01
    13:0.09
    14:0.51
    15:0.01
    Negative Logits
     much
    -0.34
     than
    -0.33
    ExtendWith
    -0.31
     so
    -0.30
     steps
    -0.29
     future
    -0.29
     fit
    -0.28
     first
    -0.28
     battle
    -0.28
     depths
    -0.28
    POSITIVE LOGITS
     dAtA
    0.42
    MessageTagHelper
    0.33
    OGND
    0.32
    findpost
    0.32
    setVerticalGroup
    0.32
    oredCriteria
    0.31
    (',');
    0.30
     AssemblyVersion
    0.30
    LEncoder
    0.30
     вікісторінку
    0.30
    Activations Density 0.286%

    No Known Activations