© 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. 12-GEMMASCOPE-RES-16K
    6. 9345
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to humanity, human rights, and the human experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respective
    -0.39
     direct
    -0.36
     boste
    -0.35
     kệ
    -0.34
    strecke
    -0.33
     Höhe
    -0.33
     review
    -0.33
     별
    -0.32
     specifico
    -0.32
     treo
    -0.32
    POSITIVE LOGITS
    Human
    1.52
    human
    1.52
     Human
    1.48
     human
    1.48
    HUMAN
    1.37
     HUMAN
    1.35
     Humans
    1.28
    Humans
    1.25
     humans
    1.22
    humans
    1.18
    Activations Density 0.124%

    No Known Activations