Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 15236
    Prev
    Next
    INDEX
    Explanations

    functions and their associated operations, particularly those related to string replacement and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -1.18
     myſelf
    -1.12
     pleaſure
    -1.10
     poffible
    -1.10
     itſelf
    -1.06
    Personensuche
    -1.02
     raiſ
    -1.02
     Efq
    -1.00
     Majefty
    -0.99
     ―――――
    -0.99
    POSITIVE LOGITS
    replace
    1.64
    Replace
    1.13
    replaceAll
    1.01
     Replace
    0.94
     replace
    0.85
    REPLACE
    0.84
    Replacing
    0.70
     REPLACE
    0.68
    gsub
    0.68
     replacing
    0.64
    Activations Density 0.038%

    No Known Activations