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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1949
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PY
    -0.65
     LY
    -0.62
     CE
    -0.62
     BE
    -0.60
     LE
    -0.60
     PA
    -0.60
     PE
    -0.59
     FA
    -0.59
     VE
    -0.59
     TE
    -0.58
    POSITIVE LOGITS
     asesinado
    0.54
     vergüenza
    0.54
     quema
    0.52
     löyty
    0.49
     huom
    0.48
     asesin
    0.47
     pelea
    0.47
     conciencia
    0.47
     leyenda
    0.47
     enamorado
    0.47
    Activations Density 1.083%

    No Known Activations