© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6436
    Prev
    Next
    INDEX
    Explanations

    numerical values and slashes that are often used as paths or delimiters in code or URLs

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

    The forward slash "/" character

    np_acts-logits-general · gemini-2.0-flash

    URLs and file paths with slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.90
     dezelve
    -0.79
     ſont
    -0.75
     Anſ
    -0.72
    Datuak
    -0.71
     ſtate
    -0.69
    躇
    -0.68
     Houſe
    -0.68
     ſche
    -0.67
    ruptedException
    -0.66
    POSITIVE LOGITS
    /
    1.23
     /
    1.19
    |/
    1.05
    {}/
    1.01
    ()/
    0.94
    -/
    0.94
    ./
    0.93
    ]/
    0.93
    '/
    0.90
    }/
    0.90
    Activations Density 0.467%

    No Known Activations