© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9243
    Prev
    Next
    INDEX
    Explanations

    terms related to "like" or comparisons, often indicating similarity or resemblance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.52
     Reiche
    -0.52
     հղումներ
    -0.47
     <>",
    -0.46
    IndentedString
    -0.43
    shund
    -0.42
    tiary
    -0.42
    NUMX
    -0.41
    eterminate
    -0.41
    شاف
    -0.41
    POSITIVE LOGITS
    like
    1.52
    LIKE
    1.09
    likes
    0.95
    liken
    0.76
    lik
    0.73
    Likes
    0.69
    Like
    0.67
    LIK
    0.61
    ähn
    0.60
    alike
    0.58
    Activations Density 0.092%

    No Known Activations