© 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. 40-GEMMASCOPE-RES-16K
    6. 2669
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "to" followed by verbs or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.62
    Tembelea
    -0.45
    __':
    -0.41
    msgTypes
    -0.41
     olev
    -0.40
    #+#
    -0.38
    getDoctrine
    -0.38
    __":
    -0.36
    grà
    -0.36
    tonode
    -0.35
    POSITIVE LOGITS
     consider
    0.73
     contend
    0.67
     boot
    0.65
     behold
    0.62
     tide
    0.57
     ponder
    0.57
     worry
    0.56
     accompany
    0.56
    consider
    0.55
     chew
    0.52
    Activations Density 0.194%

    No Known Activations