© 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. 9724
    Prev
    Next
    INDEX
    Explanations

    technical terminology and technical process descriptions

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

    followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    greeting salutation

    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
    Identyfik
    -0.63
    ActionCreators
    -0.52
    étranger
    -0.52
     ddelweddau
    -0.51
     mely
    -0.50
    binant
    -0.50
    gifter
    -0.47
    prefixer
    -0.47
    省市镇
    -0.47
    گاب
    -0.47
    POSITIVE LOGITS
    Portale
    0.72
    LayoutStyle
    0.72
    MigrationBuilder
    0.70
    JpaRepository
    0.68
    rawDesc
    0.68
     intptr
    0.67
    principalTable
    0.66
    (!__
    0.63
     صوتيه
    0.62
     <>",
    0.61
    Activations Density 2.320%

    No Known Activations