© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1447
    Prev
    Next
    INDEX
    Explanations

    instances of specialized terminology or mathematical symbols

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

    terms related to warranties and legal disclaimers

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

    implied warranty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.51
     ControllerBase
    -0.44
    unhofer
    -0.43
    IMIENTO
    -0.41
    RAFT
    -0.41
     decl
    -0.41
    atifying
    -0.40
    matorium
    -0.39
    ствий
    -0.39
    OGND
    -0.39
    POSITIVE LOGITS
     ISSN
    1.42
    ISSN
    1.37
    StoryboardSegue
    0.94
    出版年
    0.88
    tvguidetime
    0.79
     thence
    0.66
     ISBN
    0.65
    ніципа
    0.64
     EconPapers
    0.64
     mịn
    0.62
    Activations Density 0.002%

    No Known Activations