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. 458
    Prev
    Next
    INDEX
    Explanations

    attends to directory-related tokens from configuration-related tokens

    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
    0:0.01
    1:0.03
    2:0.06
    3:0.50
    4:0.03
    5:0.10
    6:0.12
    7:0.09
    Negative Logits
    InputBorder
    -0.25
    ↵↵
    -0.25
    Personendaten
    -0.24
    ed
    -0.23
     oprot
    -0.23
     suivantes
    -0.22
     bisog
    -0.22
     jesteśmy
    -0.21
    ът
    -0.21
     gefü
    -0.21
    POSITIVE LOGITS
    æus
    0.41
    æa
    0.38
    dorfer
    0.36
    msgSender
    0.36
    agascar
    0.36
    最快更新
    0.36
    kranz
    0.36
    writerow
    0.35
    ]--;
    0.34
    cerer
    0.34
    Activations Density 0.034%

    No Known Activations