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. 1272
    Prev
    Next
    INDEX
    Explanations

    attends to the token "Copyright" from arbitrary tokens that follow

    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
    0:0.02
    1:0.02
    2:0.01
    3:0.02
    4:0.03
    5:0.04
    6:0.01
    7:0.01
    8:0.03
    9:0.03
    10:0.63
    11:0.02
    12:0.01
    13:0.02
    14:0.01
    15:0.01
    Negative Logits
     Italijanski
    -0.41
    adaptiveStyles
    -0.40
     Италијани
    -0.39
    uxxxx
    -0.36
    aarrggbb
    -0.36
    ]")]
    -0.35
     '\\;'
    -0.35
    ########.
    -0.35
    windowFixed
    -0.34
     nonUne
    -0.34
    POSITIVE LOGITS
    2
    0.31
     "
    0.29
    SequentialGroup
    0.26
    A
    0.26
    i
    0.25
     Ta
    0.24
     فرض
    0.24
    Out
    0.24
    1
    0.24
    .
    0.24
    Activations Density 0.013%

    No Known Activations