© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7918
    Prev
    Next
    INDEX
    Explanations

    concepts related to physics and measurement, particularly focusing on gravity and its effects

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

    "gravity" or centrifugation

    np_acts-logits-general · gemini-2.0-flash

    gravity and scientific measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.53
    </tfoot>
    -0.48
     tartalomajánló
    -0.46
    modore
    -0.46
     fign
    -0.46
    красивые
    -0.46
     Signalez
    -0.46
    ⤹
    -0.46
    ofan
    -0.45
    Демографія
    -0.45
    POSITIVE LOGITS
     gravity
    1.66
    gravity
    1.40
     Gravity
    1.34
    Gravity
    1.27
     gravitational
    1.22
     gravedad
    1.17
     GRAV
    1.13
    GRAV
    1.03
     gravitation
    0.98
    setGravity
    0.93
    Activations Density 0.324%

    No Known Activations