© 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. 3372
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic signal processing and conversion

    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
     nakalista
    -0.54
    offsetof
    -0.49
     <<<<<<<<<<<<<<
    -0.41
     mắn
    -0.40
     مشين
    -0.38
     دیکھیے
    -0.34
     mergeFrom
    -0.34
     Reſ
    -0.33
     Inſ
    -0.33
    RefNanny
    -0.33
    POSITIVE LOGITS
     signal
    3.02
     signals
    2.98
    signal
    2.66
    signals
    2.55
     Signals
    2.47
     Signal
    2.36
    信号
    2.36
    Signals
    2.34
    Signal
    2.34
     SIGNAL
    2.25
    Activations Density 1.507%

    No Known Activations