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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6085
    Prev
    Next
    INDEX
    Explanations

    attends to the term "World" from related contextual phrases or terms appearing later

    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
    0:0.74
    1:0.01
    2:0.02
    3:0.03
    4:0.08
    5:0.03
    6:0.02
    7:0.03
    Negative Logits
    LookAnd
    -0.37
    webElementXpaths
    -0.36
     Committee
    -0.35
     resourceCulture
    -0.34
    fone
    -0.34
    cobs
    -0.32
     East
    -0.32
     Room
    -0.31
     Âge
    -0.31
    🇱
    -0.31
    POSITIVE LOGITS
     Roskov
    0.34
    @[+][
    0.34
     dedans
    0.32
    Portail
    0.32
    Przypisy
    0.31
     dietro
    0.30
     Portail
    0.30
    الإنجليزية
    0.29
     asparagus
    0.29
     firebaseConfig
    0.29
    Activations Density 0.017%

    No Known Activations