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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8272
    Prev
    Next
    INDEX
    Explanations

    references to razors and related shaving terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mierda
    -0.58
    HostException
    -0.55
    érables
    -0.55
     poussière
    -0.55
    
    -0.55
     horaire
    -0.54
    ruptcy
    -0.54
     ghoul
    -0.53
     kasarigan
    -0.53
     héri
    -0.50
    POSITIVE LOGITS
    Razor
    4.50
     Razor
    3.16
    razor
    2.53
     razor
    2.42
     RAZ
    1.41
    RAZ
    1.18
     Raz
    1.11
     raz
    1.10
    Raz
    1.04
     razer
    1.01
    Activations Density 0.002%

    No Known Activations