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. 232
    Prev
    Next
    INDEX
    Explanations

    attends to the term "issues" from related terms "issue" in contexts discussing problems or topics at hand

    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
    0:0.04
    1:0.43
    2:0.07
    3:0.04
    4:0.11
    5:0.19
    6:0.03
    7:0.04
    Negative Logits
    "?
    -0.32
     bekym
    -0.30
     Anſ
    -0.29
     noastre
    -0.29
     femininos
    -0.28
     nostru
    -0.28
     tuta
    -0.27
     particolari
    -0.27
     creș
    -0.27
    se
    -0.27
    POSITIVE LOGITS
    DockStyle
    0.47
    aarrggbb
    0.44
     Мексичка
    0.44
     disambiguazione
    0.43
    WithIOException
    0.41
     defaultstate
    0.41
    garmin
    0.40
    windowFixed
    0.40
    Vidite
    0.40
    DebuggerNonUser
    0.39
    Activations Density 0.050%

    No Known Activations