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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16240
    Prev
    Next
    INDEX
    Explanations

    references to guidance and advice across various contexts

    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
     Dix
    -0.66
     Xtreme
    -0.60
    bcryptjs
    -0.59
     Skar
    -0.59
     Sexton
    -0.57
    bcrypt
    -0.56
     Revolt
    -0.56
     Uptown
    -0.56
    ộc
    -0.55
    ể
    -0.55
    POSITIVE LOGITS
     guidance
    3.12
    guidance
    2.90
     Guidance
    2.78
    Guidance
    2.77
     GUID
    2.25
     guid
    2.21
     guiding
    2.15
    guided
    2.08
     guided
    2.07
     guides
    2.04
    Activations Density 0.057%

    No Known Activations