© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11787
    Prev
    Next
    INDEX
    Explanations

    functions related to string manipulation and replacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.63
     متعلقه
    -0.63
    intios
    -0.60
     Administrativna
    -0.57
    assertNull
    -0.57
     signin
    -0.56
     Phu
    -0.55
    (")");
    -0.55
     cerimonia
    -0.54
    featureID
    -0.54
    POSITIVE LOGITS
    replace
    2.15
    Replace
    1.70
     Replace
    1.47
    REPLACE
    1.35
    replaceAll
    1.31
     replace
    1.26
     REPLACE
    1.17
    Replacing
    1.05
     replaces
    1.04
     replacing
    1.03
    Activations Density 0.053%

    No Known Activations