© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3938
    Prev
    Next
    INDEX
    Explanations

    terms related to signals and signal processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "signal"

    np_acts-logits-general · gemini-2.0-flash

    signal and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uría
    -0.61
    helves
    -0.61
    Maur
    -0.55
     splen
    -0.55
    یریت
    -0.55
    excl
    -0.55
     thiếu
    -0.53
    HostException
    -0.52
    ecma
    -0.52
     Rowe
    -0.52
    POSITIVE LOGITS
     signals
    1.18
     Signals
    1.12
    signals
    1.12
    Signals
    1.00
     Signal
    0.99
    signal
    0.95
    SIGNAL
    0.94
     signal
    0.92
    Signal
    0.86
     SIGNAL
    0.83
    Activations Density 0.153%

    No Known Activations