© 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. 18-GEMMASCOPE-RES-16K
    11. 8795
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical power supplies and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    power or batteries

    np_acts-logits-general · gemini-2.0-flash

    powered devices and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ElementException
    -0.46
    wardship
    -0.45
    bestos
    -0.44
    żeli
    -0.43
     Hobbes
    -0.42
     consign
    -0.40
    vore
    -0.40
     estre
    -0.38
     Homer
    -0.38
     جس
    -0.38
    POSITIVE LOGITS
     disambiguazione
    1.03
     powering
    0.94
    powering
    0.82
     powered
    0.71
     lights
    0.70
     CommandType
    0.68
     illumination
    0.68
    powered
    0.68
     heating
    0.67
     lighting
    0.66
    Activations Density 0.286%

    No Known Activations