© 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. 5922
    Prev
    Next
    INDEX
    Explanations

    statistical results and numerical data in the context of analysis

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

    Numbers followed by a period

    np_acts-logits-general · gemini-2.0-flash

    numerical sequences

    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
    <bos>
    -0.68
     «
    -0.51
     “
    -0.46
    OGND
    -0.45
    \\
    -0.44
    })),
    -0.44
     "
    -0.44
    lą
    -0.44
    :「
    -0.44
    部
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.94
    ConstraintMaker
    0.89
     defaultstate
    0.86
     فريبيس
    0.83
     MainAxisSize
    0.80
    ScopeManager
    0.76
     StyleSheet
    0.76
    MemoryWarning
    0.75
    
    0.74
     الاطلاع
    0.74
    Activations Density 0.608%

    No Known Activations