© 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. 12623
    Prev
    Next
    INDEX
    Explanations

    elements related to legal and regulatory processes

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

    preceding "potential."

    np_acts-logits-general · gemini-2.0-flash

    potential clients or outcomes

    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
    Besos
    -0.46
    VolleyError
    -0.41
     PyTuple
    -0.40
     finisher
    -0.37
     Enix
    -0.37
    PRWEB
    -0.36
     cellspacing
    -0.35
     stabilized
    -0.35
     다시
    -0.34
     synced
    -0.34
    POSITIVE LOGITS
     potential
    2.33
    potential
    2.09
     prospective
    2.02
    Potential
    2.00
     Potential
    1.96
     potenciales
    1.88
     POTENTIAL
    1.82
     proposed
    1.82
     potencial
    1.77
     потенциаль
    1.74
    Activations Density 0.868%

    No Known Activations