© 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. 39-GEMMASCOPE-RES-16K
    11. 2611
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to statistical analysis methods and calibration techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nowadays
    -0.93
    Nowadays
    -0.92
     nowadays
    -0.87
     colourful
    -0.74
     instalments
    -0.73
     programmes
    -0.69
     fulfil
    -0.69
    NoOf
    -0.69
     analysing
    -0.68
     marvellous
    -0.67
    POSITIVE LOGITS
     geologic
    0.71
     hypothesized
    0.71
     betweenstory
    0.65
     zoude
    0.63
     Geologic
    0.63
     hydrologic
    0.60
     Utilizing
    0.60
     ostensibly
    0.60
     nominally
    0.59
     utilizing
    0.59
    Activations Density 4.333%

    No Known Activations