© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9775
    Prev
    Next
    INDEX
    Explanations

    expressions related to appreciation and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    TagMode
    -0.75
    FormTagHelper
    -0.70
     surla
    -0.68
    Portail
    -0.67
     kasarigan
    -0.65
    balleur
    -0.65
    EDEFAULT
    -0.64
    ftagPool
    -0.63
    exitRule
    -0.60
    enterOuterAlt
    -0.60
    POSITIVE LOGITS
     rând
    0.35
     ditto
    0.30
     хто
    0.28
     metų
    0.27
    SEM
    0.27
    相
    0.26
     also
    0.26
     grå
    0.25
     compteur
    0.25
    目
    0.25
    Activations Density 0.177%

    No Known Activations