© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7071
    Prev
    Next
    INDEX
    Explanations

    references to formal declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gard
    -0.56
    ngdoc
    -0.54
     trains
    -0.52
    comm
    -0.50
     SPOT
    -0.49
    lamp
    -0.49
    ins
    -0.49
    hod
    -0.49
    lab
    -0.48
     Gardiner
    -0.48
    POSITIVE LOGITS
     declaration
    0.93
    Declaration
    0.88
     declaración
    0.83
    declaration
    0.83
     declare
    0.79
     Declaration
    0.78
     declaração
    0.73
     DECLARATION
    0.71
     declaraciones
    0.70
     declarations
    0.69
    Activations Density 0.368%

    No Known Activations