© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8106
    Prev
    Next
    INDEX
    Explanations

    references to the effects of various factors or treatments

    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
    Bissau
    -0.94
    craper
    -0.86
    "}>
    -0.81
    bobox
    -0.81
    edicated
    -0.81
    '}>
    -0.77
     CIM
    -0.77
    monary
    -0.76
     Dumas
    -0.74
    ノロ
    -0.73
    POSITIVE LOGITS
     effects
    2.42
     effect
    2.34
     Effects
    2.25
     Effect
    2.22
    Effect
    2.16
    Effects
    2.15
    effect
    2.11
    effects
    2.09
     EFFECT
    1.98
     EFFECTS
    1.95
    Activations Density 0.103%

    No Known Activations