© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13461
    Prev
    Next
    INDEX
    Explanations

    terms related to raw materials and data

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

    The token "raw"

    np_acts-logits-general · gemini-2.0-flash

    raw data or value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TryGetValue
    -0.60
    PyErr
    -0.60
    RegistryLite
    -0.60
    HasAnnotation
    -0.59
     corporativa
    -0.57
     rinnov
    -0.56
     layui
    -0.55
    omitempty
    -0.55
     recommandée
    -0.55
    Portail
    -0.55
    POSITIVE LOGITS
     Raw
    1.43
     raw
    1.39
    Raw
    1.25
     RAW
    1.10
    RAW
    1.02
    raw
    1.01
    RawData
    0.94
     rough
    0.92
    getRaw
    0.91
    Rough
    0.90
    Activations Density 0.222%

    No Known Activations