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. 391
    Prev
    Next
    INDEX
    Explanations

    attends to the token "also" from the token ","

    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
    0:0.07
    1:0.04
    2:0.01
    3:0.01
    4:0.63
    5:0.07
    6:0.04
    7:0.09
    Negative Logits
     Majefty
    -0.49
     Efq
    -0.46
     pleaſure
    -0.45
    ſelves
    -0.44
     Jefus
    -0.43
     Monfieur
    -0.43
    ſelf
    -0.42
    esterday
    -0.41
    neſs
    -0.40
    CompilerServices
    -0.40
    POSITIVE LOGITS
    دانشنامهٔ
    0.37
    <eos>
    0.36
    XmlSchema
    0.34
    NameValuePair
    0.34
     OGSÅ
    0.32
    ))=\
    0.32
    PerformLayout
    0.32
    >)</
    0.31
    UnifiedTopology
    0.31
    temp
    0.31
    Activations Density 0.789%

    No Known Activations