© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 13400
    Prev
    Next
    INDEX
    Explanations

    terms related to manual or hand-operated activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.44
     seura
    -0.42
     ISNI
    -0.38
     liitty
    -0.38
     հղումներ
    -0.37
     במח
    -0.37
     pembe
    -0.36
    geleitet
    -0.35
     attractions
    -0.35
    gory
    -0.35
    POSITIVE LOGITS
    Hand
    1.70
     Hand
    1.69
     hand
    1.60
    hand
    1.53
    HAND
    1.44
     HAND
    1.40
     Hands
    1.39
    Hands
    1.34
     hands
    1.27
    hands
    1.27
    Activations Density 0.098%

    No Known Activations