© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7690
    Prev
    Next
    INDEX
    Explanations

    components and characteristics of shaving or grooming products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lokales
    -0.52
    SequentialGroup
    -0.49
    StructEnd
    -0.48
    mergeFrom
    -0.46
     externi
    -0.45
     createSlice
    -0.45
    ╗
    -0.45
     defaultstate
    -0.45
     Brunnen
    -0.45
    Enzo
    -0.45
    POSITIVE LOGITS
     beard
    1.27
     shaving
    1.17
     shave
    1.16
     Beard
    1.13
     beards
    1.10
     shaved
    1.06
    beard
    1.00
     mustache
    0.98
    Beard
    0.97
     moustache
    0.93
    Activations Density 0.169%

    No Known Activations