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. 201
    Prev
    Next
    INDEX
    Explanations

    attends to negation-related tokens from their affirmative counterparts

    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
    0:0.02
    1:0.59
    2:0.11
    3:0.02
    4:0.06
    5:0.05
    6:0.05
    7:0.06
    Negative Logits
     &___
    -0.96
    sizeCache
    -0.90
    RegressionTest
    -0.85
     disambiguazione
    -0.85
    tagHelperRunner
    -0.85
    principalColumn
    -0.83
    LookAnd
    -0.82
     propOrder
    -0.82
     CreateTagHelper
    -0.81
     CURIAM
    -0.80
    POSITIVE LOGITS
    1
    0.54
     
    0.53
    0
    0.48
    A
    0.47
    2
    0.46
    .
    0.45
    The
    0.45
    5
    0.43
    In
    0.42
    4
    0.42
    Activations Density 0.096%

    No Known Activations