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. 10-GEMMASCOPE-ATT-16K
    6. 6197
    Prev
    Next
    INDEX
    Explanations

    attends to the word "is" from the upcoming "so" related to seasonal excitement

    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
    1:0.11
    2:0.12
    3:0.14
    4:0.14
    5:0.03
    6:0.16
    7:0.19
    Negative Logits
    ftagPool
    -0.30
    msgTypes
    -0.27
     sẻ
    -0.24
     صوتيه
    -0.23
    )')
    -0.23
    }`}
    -0.23
    είο
    -0.23
     Gaps
    -0.22
    ugal
    -0.22
    }';
    -0.21
    POSITIVE LOGITS
     opérateur
    0.28
    ArgsConstructor
    0.27
    AndEndTag
    0.26
    balleur
    0.26
    ModelForm
    0.26
    nestjs
    0.25
     يتيمه
    0.25
    localVar
    0.25
     TextInputType
    0.24
     SafeMath
    0.24
    Activations Density 0.109%

    No Known Activations