© 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. 18-GEMMASCOPE-RES-16K
    6. 6304
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation regarding property descriptors and licensing information

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

    Formatting characters and unusual punctuation

    np_acts-logits-general · gemini-2.0-flash

    legal analysis and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.83
     
    -0.77
    ,
    -0.68
    1
    -0.67
    ↵
    -0.65
     =
    -0.63
     (
    -0.63
     .
    -0.60
    .
    -0.60
    ?
    -0.59
    POSITIVE LOGITS
     للمعارف
    1.18
    ".
    
    1.15
    ^(@)
    1.14
     ་་
    1.12
     doubtnut
    1.09
    ſelves
    1.06
     ſind
    1.06
     Мексичка
    1.05
    tvguidetime
    1.05
    تقاوى
    1.04
    Activations Density 0.127%

    No Known Activations