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. 6157
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.23
    1:0.09
    2:0.09
    3:0.12
    4:0.12
    5:0.09
    6:0.10
    7:0.11
    Negative Logits
     Signalez
    -0.55
    Архівовано
    -0.52
    transQ
    -0.51
    ):}
    -0.49
     BoxDecoration
    -0.49
    ContentAsync
    -0.48
     resourceCulture
    -0.47
    ]")]
    -0.47
    Билгалдахарш
    -0.47
    .)}
    -0.47
    POSITIVE LOGITS
    <eos>
    0.28
    (
    0.25
    h
    0.25
     by
    0.25
     
    0.25
    ...
    0.24
    <code>
    0.24
     this
    0.24
    ic
    0.23
     the
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.