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-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 6020
    Prev
    Next
    INDEX
    Explanations

    attends to the term "article" from various types of punctuation and related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 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
    1:0.03
    2:0.09
    3:0.20
    4:0.08
    5:0.07
    6:0.24
    7:0.25
    Negative Logits
    ьаж
    -0.54
     препратки
    -0.49
     esternos
    -0.47
    orsese
    -0.46
    MigrationBuilder
    -0.46
    UnsafeEnabled
    -0.44
    )‏
    -0.44
     CanadaChoose
    -0.43
    asgi
    -0.42
    Viited
    -0.40
    POSITIVE LOGITS
    deaux
    0.32
     Cap
    0.31
    bain
    0.30
    '}';
    0.30
     CreateTagHelper
    0.29
    ricle
    0.29
    Slf
    0.29
    ',
    0.29
    =*/
    0.29
    ieuses
    0.28
    Activations Density 0.651%

    No Known Activations