© 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 EvalsExportsinterp-engineNEWAPI 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. 6580
    Prev
    Next
    INDEX
    Explanations

    references to "ground" in various contexts, particularly in relation to rules, conditions, and physical states

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

    "ground" followed by specific prepositions/words

    np_acts-logits-general · gemini-2.0-flash

    ground rules, ground state, ground breaking

    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
     aarde
    -0.52
     pleaſure
    -0.48
     NDEBUG
    -0.44
    Earth
    -0.44
    ſelf
    -0.42
     ioutil
    -0.42
     earth
    -0.41
    ไง
    -0.41
     leſs
    -0.41
    rrggbb
    -0.40
    POSITIVE LOGITS
     Mad
    0.60
    __(/*!
    0.59
     mad
    0.57
    Mad
    0.56
    存于互联网档案馆
    0.50
    mad
    0.47
    TintMode
    0.46
     متعلقه
    0.44
     MAD
    0.43
    agascar
    0.43
    Activations Density 0.072%

    No Known Activations