© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15695
    Prev
    Next
    INDEX
    Explanations

    themes of improvement and progression in relationships and situations

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

    Preceding tokens of "level"

    np_acts-logits-general · gemini-2.0-flash

    level progression

    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
    mtable
    -0.46
    <?
    -0.44
     يتيمه
    -0.44
    IConfiguration
    -0.43
    YMMV
    -0.41
    Бахар
    -0.41
     الدولى
    -0.41
    こんにちは
    -0.41
     Vitro
    -0.38
    akaan
    -0.38
    POSITIVE LOGITS
     level
    1.22
    level
    1.05
     LEVEL
    1.04
     levels
    1.00
     Level
    0.97
    LEVEL
    0.95
    Level
    0.95
    レベル
    0.93
     niveau
    0.90
     livello
    0.87
    Activations Density 0.096%

    No Known Activations