© 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. 37-GEMMASCOPE-RES-16K
    6. 3662
    Prev
    Next
    INDEX
    Explanations

    terms related to pressing and releasing actions, particularly in the context of devices and their functions

    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
    MergeFrom
    -0.40
    Datuak
    -0.38
    клопе
    -0.38
     titolata
    -0.37
    oa̍t
    -0.36
     pohod
    -0.36
    FieldDescriptor
    -0.36
     råd
    -0.35
     tatuagem
    -0.35
    óstico
    -0.35
    POSITIVE LOGITS
     release
    3.91
     Release
    3.50
    release
    3.38
     releases
    3.38
     released
    3.36
    Release
    3.33
     RELEASE
    3.19
     releasing
    3.17
     Releases
    2.94
     Released
    2.91
    Activations Density 1.103%

    No Known Activations