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. 1347
    Prev
    Next
    INDEX
    Explanations

    attends to the mention of "Handler" from instances of "close," "Builder," or "get" found later in the text

    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
    0:0.03
    1:0.03
    2:0.02
    3:0.08
    4:0.01
    5:0.01
    6:0.06
    7:0.09
    8:0.01
    9:0.02
    10:0.02
    11:0.02
    12:0.08
    13:0.26
    14:0.18
    15:0.01
    Negative Logits
    WebElementEntity
    -0.77
     好文分享
    -0.74
     Dieſe
    -0.74
     パンチラ
    -0.74
     geweſen
    -0.73
    MethodManager
    -0.73
    bildtitel
    -0.73
     ſeyn
    -0.73
     nahil
    -0.73
    <unused22>
    -0.73
    POSITIVE LOGITS
    </em>
    0.30
    ↵
    0.28
     
    0.22
    0
    0.22
    }}}$
    0.21
    ])+
    0.21
    ">)</
    0.20
     p
    0.20
    ']):
    0.19
     the
    0.19
    Activations Density 0.199%

    No Known Activations