© 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. 15034
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual representations and observations

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

    Prepositions related to surfaces

    np_acts-logits-general · gemini-2.0-flash

    writing on walls

    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
    ɵ
    -0.56
    ImageContext
    -0.50
    Sitz
    -0.49
     Romagna
    -0.49
     vectorielles
    -0.46
    ęki
    -0.45
    ∧
    -0.45
     Laid
    -0.45
     Herring
    -0.44
     bougies
    -0.44
    POSITIVE LOGITS
     walls
    1.42
     wall
    1.31
    walls
    1.18
     Walls
    1.12
    wall
    1.07
    Walls
    1.04
     Wall
    1.02
     WALL
    0.99
    Wall
    0.94
     dinding
    0.90
    Activations Density 0.279%

    No Known Activations