© 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. 1-GEMMASCOPE-RES-16K
    11. 9922
    Prev
    Next
    INDEX
    Explanations

    the concept of "quality" or "attributes of entities."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SafeMath
    -0.65
    יצוב
    -0.63
     sols
    -0.63
     onCreateView
    -0.61
     gaf
    -0.56
     Isolation
    -0.55
    nyv
    -0.53
    brl
    -0.52
     NSCoder
    -0.52
     Bosco
    -0.51
    POSITIVE LOGITS
    ality
    4.26
    ALITY
    3.04
    alities
    2.92
    uality
    1.45
    nalité
    1.19
    icity
    1.19
    lity
    1.17
    alty
    1.12
    alité
    1.07
    ITY
    1.05
    Activations Density 0.119%

    No Known Activations