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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2816
    Prev
    Next
    INDEX
    Explanations

    terms related to limitations or deficiencies in scientific research

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

    introduces explanation because

    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
    rungsseite
    -0.65
    abestanden
    -0.63
     parseFrom
    -0.56
    findpost
    -0.55
    stateProvider
    -0.54
    constructor
    -0.53
    Filmografie
    -0.52
    setdefault
    -0.52
    interopRequire
    -0.51
    makeConstraints
    -0.50
    POSITIVE LOGITS
     because
    3.77
    because
    3.33
     porque
    3.03
    Because
    2.96
     Because
    2.89
     karena
    2.84
     BECAUSE
    2.81
    因为
    2.62
     perché
    2.61
     потому
    2.60
    Activations Density 4.805%

    No Known Activations