© 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. 37-GEMMASCOPE-RES-16K
    11. 5787
    Prev
    Next
    INDEX
    Explanations

    code snippets and commands related to data handling and error management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.49
    显然
    -0.44
     OMITBAD
    -0.44
     pungkas
    -0.42
    //};
    -0.41
    putchar
    -0.41
     Ibidem
    -0.41
     newState
    -0.40
    ?!?
    -0.40
     exposition
    -0.39
    POSITIVE LOGITS
     upto
    0.82
     atleast
    0.74
    upto
    0.70
     wastage
    0.69
    Mumbai
    0.68
    engg
    0.68
     Abhishek
    0.68
    Contd
    0.67
     irrespective
    0.66
     Khur
    0.65
    Activations Density 0.218%

    No Known Activations