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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6471
    Prev
    Next
    INDEX
    Explanations

    attends to affirmative states from negated or contradicted states

    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
    0:0.12
    1:0.16
    2:0.10
    3:0.12
    4:0.13
    5:0.05
    6:0.11
    7:0.16
    Negative Logits
     AssemblyVersion
    -0.41
     ++)
    -0.40
     CreateTagHelper
    -0.40
    berdayakan
    -0.37
    RenderAtEndOf
    -0.35
     betweenstory
    -0.35
     kasarigan
    -0.34
    SharedDtor
    -0.34
    FormTagHelper
    -0.33
    JspWriter
    -0.32
    POSITIVE LOGITS
     Quelles
    0.21
    ({});
    0.20
     Freih
    0.20
     <<<<<<<<<<<<<<
    0.20
     Their
    0.20
    Super
    0.19
     Super
    0.19
    Their
    0.19
    ustain
    0.18
     shared
    0.18
    Activations Density 0.340%

    No Known Activations