© 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. 11003
    Prev
    Next
    INDEX
    Explanations

    instances of the word "call" and its variations, indicating a focus on the concept of calling out or invoking

    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
     énergé
    -0.56
    ymce
    -0.55
     médicaux
    -0.46
     contemporaine
    -0.44
    curkan
    -0.42
     húmedo
    -0.40
     فريبيس
    -0.39
     pauvres
    -0.39
     réussir
    -0.39
     elämä
    -0.38
    POSITIVE LOGITS
     call
    1.64
    call
    1.60
    Call
    1.55
     Call
    1.55
     CALL
    1.52
    CALL
    1.45
     Calls
    1.39
     calls
    1.36
    calls
    1.32
    Calls
    1.24
    Activations Density 0.154%

    No Known Activations