© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3278
    Prev
    Next
    INDEX
    Explanations

    terms related to user interactions and queries within a digital context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behoort
    -0.67
     poichè
    -0.63
    oarece
    -0.61
     számára
    -0.60
    /*---
    -0.59
     alcuna
    -0.59
    reiras
    -0.58
     dàng
    -0.58
     suivantes
    -0.58
     hieronder
    -0.57
    POSITIVE LOGITS
     dig
    0.70
     shit
    0.67
     thing
    0.66
     overdo
    0.66
     Pascual
    0.66
     fucking
    0.63
    Dig
    0.61
     spoil
    0.60
     stuck
    0.60
     dug
    0.59
    Activations Density 0.296%

    No Known Activations