© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 15267
    Prev
    Next
    INDEX
    Explanations

    instances of the word "replace" and its variations related to substitution or alteration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewInit
    -0.80
     Италијани
    -0.79
    providedIn
    -0.78
    IsInitialized
    -0.77
    expandindo
    -0.74
    Portale
    -0.74
    rungsseite
    -0.74
     defStyleAttr
    -0.73
    sidemargin
    -0.72
    ->__
    -0.71
    POSITIVE LOGITS
     Replace
    1.64
     replacement
    1.58
     replace
    1.55
    Replace
    1.52
     replacing
    1.50
     Replacement
    1.48
     replacements
    1.46
     REPLACE
    1.45
     replaces
    1.44
    Replacing
    1.44
    Activations Density 0.099%

    No Known Activations