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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6623
    Prev
    Next
    INDEX
    Explanations

    attends to the word "otherwise" from corresponding conditional words or phrases that suggest an alternative or exception

    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
    0:0.08
    1:0.08
    2:0.09
    3:0.42
    4:0.09
    5:0.02
    6:0.08
    7:0.10
    Negative Logits
     <=",
    -0.45
    diyesi
    -0.43
     AssemblyCulture
    -0.42
     jScrollPane
    -0.42
     Roskov
    -0.41
     الحره
    -0.40
     Walkover
    -0.39
     >=",
    -0.39
     вікі
    -0.39
    abestanden
    -0.39
    POSITIVE LOGITS
    stdc
    0.38
     parity
    0.34
    //
    0.33
     gants
    0.33
    crollView
    0.32
     navideños
    0.32
    ิลป
    0.32
    ?—
    0.31
    MigrationBuilder
    0.30
     őket
    0.30
    Activations Density 0.291%

    No Known Activations