© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    mentions of advantages and disadvantages in various contexts

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

    Followed by ordinal adverbs ("first", "firstly")

    np_acts-logits-general · gemini-2.0-flash

    firstly, first, specifically

    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
    SourceChecksum
    -1.20
    Portale
    -0.97
     Efq
    -0.97
    tagHelperRunner
    -0.89
    IContainer
    -0.88
    GEBURTSDATUM
    -0.87
    Personendaten
    -0.85
    +#+#
    -0.84
     صوتيه
    -0.84
     ComVisible
    -0.84
    POSITIVE LOGITS
     Firstly
    1.07
    Firstly
    1.02
     firstly
    0.85
    まず
    0.82
    首先
    0.81
     First
    0.79
    First
    0.74
     first
    0.72
     including
    0.72
    一是
    0.71
    Activations Density 0.453%

    No Known Activations