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. 1-GEMMASCOPE-RES-16K
    6. 6188
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "children"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -1.05
    EDEFAULT
    -0.84
    rungsseite
    -0.84
    :✨
    -0.77
    SourceChecksum
    -0.75
    stateMutability
    -0.75
     ExecuteAsync
    -0.73
     nahilalakip
    -0.71
    rawDesc
    -0.70
     disambiguazione
    -0.68
    POSITIVE LOGITS
    s
    0.63
     vertically
    0.60
    ngOn
    0.57
    ={`${
    0.53
    ตน
    0.53
    doria
    0.52
    ={`
    0.52
     CURIAM
    0.50
    romyalgia
    0.50
    íts
    0.47
    Activations Density 0.188%

    No Known Activations