© 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. 20-GEMMASCOPE-RES-16K
    11. 2670
    Prev
    Next
    INDEX
    Explanations

    technical and procedural terms related to processes and systems

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

    Tokens that precede URLs or code snippets

    np_acts-logits-general · gemini-2.0-flash

    reflexive 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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ISNI
    -0.68
    colgroup
    -0.62
    Erreferentziak
    -0.62
    TargetException
    -0.58
    yntaxException
    -0.58
     trattano
    -0.56
     EnglishChoose
    -0.56
    CodeAttribute
    -0.55
    GraphicsUnit
    -0.55
     дописавши
    -0.53
    POSITIVE LOGITS
     itself
    1.30
    itself
    0.87
     Itself
    0.81
     stesso
    0.75
     stessa
    0.71
     heen
    0.66
     itse
    0.66
     themselves
    0.59
     proprement
    0.59
    évaluateur
    0.58
    Activations Density 1.532%

    No Known Activations