© 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. 584
    Prev
    Next
    INDEX
    Explanations

    terms related to external entities and references in scientific or technical contexts

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

    terms related to extensions and distance measurements

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

    word parts and continuations

    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
    Portail
    -0.63
    -------
    -0.63
    saraba
    -0.56
     desto
    -0.55
     Malte
    -0.55
    Continues
    -0.52
    хани
    -0.52
     Leider
    -0.51
     quadruple
    -0.50
     Tapatalk
    -0.50
    POSITIVE LOGITS
     vostri
    0.68
     enää
    0.66
    RegressionTest
    0.60
     îmb
    0.59
     Assn
    0.58
    RTLD
    0.54
     mukana
    0.54
     Soc
    0.54
    Soc
    0.53
    lloworld
    0.53
    Activations Density 0.205%

    No Known Activations