© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7279
    Prev
    Next
    INDEX
    Explanations

    quantitative data and measurements related to various studies and analyses

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

    followed by the preposition "of" or "in"

    np_acts-logits-general · gemini-2.0-flash

    these words followed by prepositions

    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
     kasarigan
    -0.60
    multer
    -0.49
    fett
    -0.47
    Хьажоргаш
    -0.45
    Referanser
    -0.45
    Clik
    -0.44
     Chriftian
    -0.43
    ukone
    -0.42
    ArrowToggle
    -0.42
    IVEREF
    -0.42
    POSITIVE LOGITS
     azonban
    0.58
     inoltre
    0.57
     hierbei
    0.54
     infatti
    0.53
     hierzu
    0.50
     however
    0.50
     tuttavia
    0.49
     allerdings
    0.48
     však
    0.48
     ayrıca
    0.47
    Activations Density 0.811%

    No Known Activations