© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 485
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and comparisons related to physical properties

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

    Superscript numbers

    np_acts-logits-general · gemini-2.0-flash

    old rats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ReusableCell
    -0.59
    MultipartFile
    -0.49
    AddTagHelper
    -0.47
    dihydro
    -0.45
    URLException
    -0.45
     informée
    -0.44
     Autorizaciones
    -0.44
     <<<<<<<<<<<<<<
    -0.44
     Arrays
    -0.43
    UserScript
    -0.43
    POSITIVE LOGITS
    writeFieldEnd
    0.48
     sentimientos
    0.47
     ángeles
    0.45
     szóci
    0.45
     béisbol
    0.44
     artesanía
    0.44
    équi
    0.44
     bailando
    0.43
    ferential
    0.43
     varones
    0.43
    Activations Density 1.235%

    No Known Activations