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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1216
    Prev
    Next
    INDEX
    Explanations

    attends to the token "el" from a variety of tokens that include a terminal or closing bracket

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.00
    1:0.01
    2:0.63
    3:0.07
    4:0.01
    5:0.00
    6:0.01
    7:0.01
    8:0.00
    9:0.01
    10:0.01
    11:0.00
    12:0.01
    13:0.07
    14:0.05
    15:0.01
    Negative Logits
    RenderAtEndOf
    -0.43
    ChildScrollView
    -0.43
     snippetHide
    -0.42
    lapsingToolbar
    -0.41
    HtmlAttribute
    -0.40
     GenerationType
    -0.39
    StoryboardSegue
    -0.39
    IUrlHelper
    -0.39
     Administrativna
    -0.39
     noDo
    -0.38
    POSITIVE LOGITS
     each
    0.18
    ณี
    0.17
     such
    0.17
    ąp
    0.17
     siinä
    0.15
     sobą
    0.15
    ąpi
    0.14
     Danach
    0.14
     jį
    0.14
    rungsseite
    0.14
    Activations Density 0.014%

    No Known Activations