© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13472
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships, impacts, or connections between various subjects

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

    Follows a noun/pronoun with a verb

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agin
    -0.45
    phrodite
    -0.44
    ÂN
    -0.44
    yz
    -0.44
    judice
    -0.43
    Anhalt
    -0.43
    agi
    -0.43
     Revi
    -0.43
     Gente
    -0.43
    juna
    -0.42
    POSITIVE LOGITS
     ModelExpression
    0.86
    BeginContext
    0.78
     mať
    0.67
    ConstraintMaker
    0.64
     berikan
    0.63
     diberikan
    0.63
    ništ
    0.63
     accorded
    0.62
     punya
    0.62
     MainAxisSize
    0.61
    Activations Density 0.347%

    No Known Activations