© 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. 16-GEMMASCOPE-RES-16K
    6. 8639
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and statistics related to comparisons or evaluations

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

    followed by forms of "to be"

    np_acts-logits-general · gemini-2.0-flash

    percentage of cost or area

    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
    WriteAttribute
    -0.82
    principalColumn
    -0.68
     فريبيس
    -0.68
     Efq
    -0.66
     GeoNames
    -0.61
    zma
    -0.60
    InstrumentedTest
    -0.58
     الدولى
    -0.57
     ſeveral
    -0.57
    Ỉ
    -0.57
    POSITIVE LOGITS
     unacc
    0.47
     typelib
    0.45
     (~
    0.44
    RequestOptions
    0.43
     gone
    0.42
     coming
    0.42
    Caractéristiques
    0.42
    ieteur
    0.41
     devoted
    0.41
     came
    0.40
    Activations Density 0.481%

    No Known Activations