© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8830
    Prev
    Next
    INDEX
    Explanations

    technical terms related to outputs and signal processing in electronic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.54
    PickerController
    -0.54
     inoxydable
    -0.50
    jupiter
    -0.45
    IntoConstraints
    -0.43
    brainer
    -0.43
     DriverManager
    -0.42
     TextFormField
    -0.42
    nasi
    -0.42
     łat
    -0.42
    POSITIVE LOGITS
     output
    1.73
     Output
    1.67
    Output
    1.59
    output
    1.58
     OUTPUT
    1.43
     outputs
    1.38
    OUTPUT
    1.36
    getOutput
    1.35
     Outputs
    1.34
    outputs
    1.25
    Activations Density 0.129%

    No Known Activations