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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14936
    Prev
    Next
    INDEX
    Explanations

    references to websites or online services in the context of business and design needs

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

    Critiques or limitations

    np_acts-logits-general · gemini-2.0-flash

    inaccurate or lacking information

    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
     صوتيه
    -0.54
    AndEndTag
    -0.54
    ArgsConstructor
    -0.53
    OGND
    -0.50
    ślę
    -0.49
    клопе
    -0.49
     ProtoMessage
    -0.47
    wiście
    -0.47
     surla
    -0.46
     unharmed
    -0.46
    POSITIVE LOGITS
     lacks
    1.53
     lack
    1.50
     insufficient
    1.41
     lacked
    1.38
     inadequate
    1.34
     lacking
    1.32
     inadequ
    1.23
    缺乏
    1.18
     poorly
    1.18
    lack
    1.11
    Activations Density 2.042%

    No Known Activations