© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8514
    Prev
    Next
    INDEX
    Explanations

    concepts related to authority and judgment

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

    Follows punctuation in activating texts

    np_acts-logits-general · gemini-2.0-flash

    words ending with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atención
    -0.47
    scrapy
    -0.45
    AndroidJUnit
    -0.45
     Raoul
    -0.44
     bVar
    -0.44
     XNUMX
    -0.44
     jadx
    -0.43
    笊
    -0.43
     leva
    -0.43
    mmate
    -0.42
    POSITIVE LOGITS
     transfieras
    0.54
    IUrlHelper
    0.53
    LookAnd
    0.46
     Normdatei
    0.46
    Datuak
    0.46
    didSet
    0.43
     EconPapers
    0.43
    ="@+
    0.43
    tinyos
    0.41
    MemoryWarning
    0.40
    Activations Density 0.041%

    No Known Activations