Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12505
    Prev
    Next
    INDEX
    Explanations

    requests for financial contributions and support for various causes

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

    Donations, amounts, and giving back

    np_acts-logits-general · gemini-2.0-flash

    donate amount

    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
    QX
    -0.34
    ContentAsync
    -0.33
    夙
    -0.33
     conosco
    -0.32
     Fall
    -0.32
     Sputnik
    -0.31
     nearly
    -0.31
     Meld
    -0.30
     p
    -0.30
     chóng
    -0.30
    POSITIVE LOGITS
     donations
    1.39
     donation
    1.23
     Donations
    1.16
     donate
    1.13
    Donations
    1.11
     Donation
    1.06
     donating
    1.03
    Donation
    0.99
    donation
    0.98
     donated
    0.98
    Activations Density 0.067%

    No Known Activations