Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11054
    Prev
    Next
    INDEX
    Explanations

    references to grooming tools and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externi
    -0.46
     createSlice
    -0.45
    protoimpl
    -0.44
    SequentialGroup
    -0.43
    oneofs
    -0.43
    Enzo
    -0.43
    Биография
    -0.42
    vece
    -0.40
    ViewInit
    -0.40
     StatefulWidget
    -0.39
    POSITIVE LOGITS
     beard
    1.74
     beards
    1.49
     Beard
    1.42
     mustache
    1.36
     shave
    1.36
    beard
    1.34
     shaving
    1.32
     moustache
    1.30
    Beard
    1.30
     shaved
    1.22
    Activations Density 0.160%

    No Known Activations