Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14741
    Prev
    Next
    INDEX
    Explanations

    references to academic and scientific terms or entities, particularly in the context of research publications and methodologies

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

    "M" followed by a capitalized letter and other letters

    np_acts-logits-general · gemini-2.0-flash

    M. or md

    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
     AssemblyCompany
    -1.11
    __(/*!
    -1.01
     onCreateView
    -0.80
    ⓘ
    -0.80
    enumi
    -0.80
     kaynağından
    -0.75
    躇
    -0.75
     Normdatei
    -0.74
    (!__
    -0.74
     JpaRepository
    -0.71
    POSITIVE LOGITS
     Madness
    1.06
     getM
    0.93
     Mayhem
    0.92
     madness
    0.74
     Moments
    0.74
    Madness
    0.73
     M
    0.71
     MAD
    0.69
     mayhem
    0.68
    ConstraintMaker
    0.68
    Activations Density 2.918%

    No Known Activations