© 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. 1-GEMMASCOPE-RES-16K
    6. 3898
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to control and management processes within systems or groups

    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
    lorus
    -0.50
    sellors
    -0.41
     trưng
    -0.40
    atol
    -0.40
     giy
    -0.39
     
    -0.39
    ména
    -0.39
    بران
    -0.38
     branches
    -0.38
    gymn
    -0.38
    POSITIVE LOGITS
     autorytatywna
    0.96
     ویکی‌پدیا
    0.89
     Efq
    0.85
     nakalista
    0.85
    imageshack
    0.82
    ⓧ
    0.80
    enumi
    0.79
     snippetHide
    0.79
     duquel
    0.77
     enfans
    0.76
    Activations Density 3.368%

    No Known Activations