© 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. 8240
    Prev
    Next
    INDEX
    Explanations

    phrases related to probability and selection processes

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

    Probability of picking letters

    np_acts-logits-general · gemini-2.0-flash

    probability of picking

    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
    تقاوى
    -1.28
    MigrationBuilder
    -1.19
     صوتيه
    -1.17
    脚注の使い方
    -1.17
     surla
    -1.17
     '\\;'
    -1.10
    +#+#
    -1.06
    AddTagHelper
    -1.05
    ChildScrollView
    -1.02
    AccessorTable
    -0.99
    POSITIVE LOGITS
     a
    0.74
    的是
    0.67
     
    0.67
    :
    0.66
     the
    0.63
     an
    0.60
     either
    0.57
     "
    0.52
     to
    0.51
     on
    0.50
    Activations Density 0.706%

    No Known Activations