Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-ATT-16K
    6. 6425
    Prev
    Next
    INDEX
    Explanations

    attends to tokens indicating purpose or reason from tokens referring to potential actions or outcomes

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.23
    1:0.28
    2:0.10
    3:0.07
    4:0.03
    5:0.02
    6:0.04
    7:0.19
    Negative Logits
     makeStyles
    -0.30
     Patria
    -0.26
    didSet
    -0.26
    cado
    -0.26
    heide
    -0.24
    rostis
    -0.24
    offsetTop
    -0.23
    kuti
    -0.23
     getSession
    -0.23
    doi
    -0.23
    POSITIVE LOGITS
     незавершена
    0.43
    Brainz
    0.42
    ValueStyle
    0.41
    Hauptartikel
    0.41
     Normdatei
    0.41
     nahilalakip
    0.38
    EDEFAULT
    0.38
     gyhoeddwyd
    0.36
     Wikimedijinoj
    0.36
     MainAxisSize
    0.36
    Activations Density 0.106%

    No Known Activations