© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12495
    Prev
    Next
    INDEX
    Explanations

    references to programming and technical instructions

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

    Followed by a question

    np_acts-logits-general · gemini-2.0-flash

    common phrases and question starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.72
    antaranya
    -0.65
    +#+#
    -0.55
    OGND
    -0.51
    
    -0.50
     Flasche
    -0.49
     titoli
    -0.48
     Ausdrücke
    -0.47
     rodillas
    -0.47
    TryDecodeAsNil
    -0.47
    POSITIVE LOGITS
     SEO
    0.51
     WordPress
    0.49
    <eos>
    0.48
     CBSE
    0.47
     😘
    0.45
    offsetWidth
    0.44
    <unused63>
    0.44
     wordpress
    0.44
     GOP
    0.44
     JavaScript
    0.43
    Activations Density 2.000%

    No Known Activations