© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 63
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols within the text

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

    types of forward slashes used in text

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

    he/she/his/her pronouns

    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
    Geplaatst
    -0.79
     متعلقه
    -0.74
    PreferredItem
    -0.72
     Roskov
    -0.70
    ativement
    -0.68
    __':
    -0.67
     Efq
    -0.65
    tanleria
    -0.65
     lenker
    -0.64
     CreateTagHelper
    -0.63
    POSITIVE LOGITS
    e
    0.49
    gex
    0.42
     Cypri
    0.42
     perdere
    0.41
    he
    0.41
    weise
    0.41
    fromCharCode
    0.40
    He
    0.40
    期刊论文
    0.40
    his
    0.39
    Activations Density 0.014%

    No Known Activations