© 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 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. 10203
    Prev
    Next
    INDEX
    Explanations

    emphasized adjectives highlighting significance or value

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

    Importance or necessity

    np_acts-logits-general · gemini-2.0-flash

    importance and necessity

    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
     Administrativna
    -0.48
    webElementGuid
    -0.46
     AssemblyVersion
    -0.42
     ReactDOM
    -0.42
     esq
    -0.39
    rungsseite
    -0.39
     AssemblyCompany
    -0.39
     Meksiku
    -0.39
    (&:
    -0.38
    RuleContext
    -0.38
    POSITIVE LOGITS
    ly
    0.59
    的一种
    0.55
     thing
    0.54
     enough
    0.53
     for
    0.51
    arangay
    0.49
    ßig
    0.47
     practice
    0.46
     behaviour
    0.45
    Palmar
    0.45
    Activations Density 0.439%

    No Known Activations