© 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. 20-GEMMASCOPE-RES-16K
    11. 7021
    Prev
    Next
    INDEX
    Explanations

    the presence of significant data entries or findings in research contexts

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

    Numbers used in calculations/comparisons

    np_acts-logits-general · gemini-2.0-flash

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hào
    -0.44
    DebuggerNonUser
    -0.40
    ="@+
    -0.39
    tika
    -0.38
    SuppressMessage
    -0.38
    Einf
    -0.38
     卷
    -0.37
    reciate
    -0.36
    ارع
    -0.36
     corre
    -0.36
    POSITIVE LOGITS
    SPATH
    0.85
    StoreMessageInfo
    0.80
    BeginContext
    0.75
     للمعارف
    0.72
    AddTagHelper
    0.64
    IVEREF
    0.64
    SequentialGroup
    0.63
    SharedCtor
    0.62
    Халык
    0.60
    Tembelea
    0.59
    Activations Density 0.153%

    No Known Activations