© 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. 12-GEMMASCOPE-RES-16K
    11. 5903
    Prev
    Next
    INDEX
    Explanations

    terms related to software assembly metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.86
     
    -0.85
    ↵
    -0.84
    .
    -0.83
    <eos>
    -0.81
    ↵↵
    -0.79
    on
    -0.79
     A
    -0.76
    ,
    -0.73
     I
    -0.73
    POSITIVE LOGITS
    +#+#
    3.53
     EconPapers
    3.35
    SourceChecksum
    3.28
     فريبيس
    3.25
    RenderAtEndOf
    3.10
    expandindo
    3.10
     resourceCulture
    3.06
     المعيارى
    3.04
     виправивши
    3.02
     CreateTagHelper
    2.98
    Activations Density 0.005%

    No Known Activations