© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5344
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "signal" and its variations, particularly in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fraî
    -0.84
    rawDesc
    -0.80
     Esau
    -0.78
    principalTable
    -0.73
     BoxFit
    -0.69
     Mame
    -0.69
    AsUp
    -0.68
    Ques
    -0.68
    quake
    -0.68
     payé
    -0.67
    POSITIVE LOGITS
     Signals
    0.99
     Signal
    0.93
     signals
    0.91
    signal
    0.90
    signals
    0.89
    Forest
    0.88
     Forest
    0.87
    SIGNAL
    0.86
    Signals
    0.85
     signal
    0.84
    Activations Density 0.116%

    No Known Activations