© 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. 14909
    Prev
    Next
    INDEX
    Explanations

    content related to financial and tax issues

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

    Government agencies or programs

    np_acts-logits-general · gemini-2.0-flash

    negative government or corporate entities

    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
    mektedir
    -0.62
    maktadır
    -0.60
     Additionally
    -0.59
     utilizing
    -0.59
     również
    -0.58
    较为
    -0.57
     utilized
    -0.56
     sahiptir
    -0.56
     endast
    -0.56
     utilize
    -0.55
    POSITIVE LOGITS
     stuff
    1.35
     freakin
    1.27
     crappy
    1.25
     thingy
    1.23
     freaking
    1.19
     dudes
    1.18
     weird
    1.12
     goddamn
    1.10
     lousy
    1.09
     crazy
    1.06
    Activations Density 6.600%

    No Known Activations