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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4374
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'i' in various contexts

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

    The letter "i" in code or math snippets

    np_acts-logits-general · gemini-2.0-flash

    index i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    d
    -0.93
    m
    -0.77
    t
    -0.75
    g
    -0.65
    l
    -0.61
     Gnaden
    -0.60
    k
    -0.59
    adaptiveStyles
    -0.58
    ScopeManager
    -0.58
    AutoScaleMode
    -0.57
    POSITIVE LOGITS
     iVar
    0.68
     am
    0.53
     beauté
    0.48
    excl
    0.48
     dieux
    0.46
    cicle
    0.45
    teams
    0.45
     Am
    0.45
     griega
    0.44
    rille
    0.43
    Activations Density 0.177%

    No Known Activations