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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 665
    Prev
    Next
    INDEX
    Explanations

    expressions of personal preferences and experiences related to technology

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

    Discussion of personal devices

    np_acts-logits-general · gemini-2.0-flash

    switch or tinker with devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Menschen
    -0.45
     numerus
    -0.44
    TextSpan
    -0.43
     <<<<<<<<<<<<<<
    -0.41
     mennesker
    -0.41
     menschen
    -0.39
     JpaRepository
    -0.39
     pendidikan
    -0.38
    ResponseBody
    -0.38
     mennes
    -0.37
    POSITIVE LOGITS
     modded
    0.46
    AntiForgeryToken
    0.46
     tinker
    0.45
     kasarigan
    0.45
     switch
    0.42
     Switch
    0.42
    Migrate
    0.42
     mojo
    0.41
     switches
    0.40
    switch
    0.40
    Activations Density 0.175%

    No Known Activations