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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 10488
    Prev
    Next
    INDEX
    Explanations

    conditional statements in code

    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
    ניס
    -0.51
    /_
    -0.48
    IBase
    -0.47
     Nis
    -0.46
     blocks
    -0.45
     abzu
    -0.44
    nato
    -0.44
    schuh
    -0.44
    setOpaque
    -0.44
     Garfield
    -0.44
    POSITIVE LOGITS
    if
    1.44
    帖最后由
    0.93
    WebVitals
    0.88
    enumi
    0.87
    enumii
    0.84
    styleType
    0.81
     оригіналу
    0.81
     if
    0.80
    IsContent
    0.80
    ParallelGroup
    0.75
    Activations Density 0.049%

    No Known Activations