Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5927
    Prev
    Next
    INDEX
    Explanations

    technical terms and discussions related to networking and telecommunications

    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
    secuencias
    -0.31
    RTSC
    -0.31
    StructEnd
    -0.29
     retrouve
    -0.29
     remonter
    -0.29
     cambia
    -0.28
    EDEFAULT
    -0.27
    ajuku
    -0.27
    льевич
    -0.27
     kasarigan
    -0.26
    POSITIVE LOGITS
     pilot
    1.99
     prototype
    1.87
     prototypes
    1.77
    pilot
    1.72
     piloto
    1.68
     Pilot
    1.68
    Pilot
    1.61
     trial
    1.58
     pilote
    1.55
     pilots
    1.54
    Activations Density 1.105%

    No Known Activations