© 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. 2-GEMMASCOPE-RES-16K
    11. 4497
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "twist" and its related forms 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.63
    Jeografia
    -0.56
    PYX
    -0.54
    Tikang
    -0.49
     Autorizaciones
    -0.48
     SEDS
    -0.48
    istoitu
    -0.46
    GHIJKLM
    -0.45
     occaf
    -0.44
     resourceCulture
    -0.43
    POSITIVE LOGITS
     sword
    0.70
     Sword
    0.69
     knee
    0.62
    Sword
    0.62
     Knee
    0.59
    Knee
    0.59
    ath
    0.57
    textBox
    0.57
     Mercy
    0.57
     radar
    0.56
    Activations Density 0.305%

    No Known Activations