© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 13829
    Prev
    Next
    INDEX
    Explanations

    phrases related to validation and criteria for assessment

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

    preceding pronouns

    np_acts-logits-general · gemini-2.0-flash

    qualities inherent, results showed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.69
     Houſe
    -0.67
     houſe
    -0.64
     ſeveral
    -0.64
    gameserver
    -0.63
     Majefty
    -0.62
     greateſt
    -0.61
     Reſ
    -0.60
     ſever
    -0.59
     pleaſure
    -0.59
    POSITIVE LOGITS
     we
    1.23
     that
    1.21
     you
    1.18
     they
    1.00
     everyone
    0.80
     someone
    0.78
     he
    0.78
    principalTable
    0.73
     I
    0.70
     she
    0.70
    Activations Density 0.348%

    No Known Activations