© 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. 220
    Prev
    Next
    INDEX
    Explanations

    phrases referring to movement or transitions related to stairs and levels within a building

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

    stairs or staircases

    np_acts-logits-general · gemini-2.0-flash

    stairs, staircase, stairway

    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
    readystatechange
    -0.64
     underv
    -0.63
    \{\\
    -0.63
    interopRequire
    -0.61
    jsonwebtoken
    -0.60
     Midas
    -0.58
     JpaRepository
    -0.57
    SpringBootTest
    -0.56
     {}));
    -0.56
    RectangleBorder
    -0.56
    POSITIVE LOGITS
     stairs
    1.91
     staircase
    1.72
     stair
    1.59
     stairway
    1.58
     Stairs
    1.57
     Stair
    1.45
    Stairs
    1.41
    Stair
    1.35
    stairs
    1.31
    stair
    1.29
    Activations Density 0.136%

    No Known Activations