© 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. 1556
    Prev
    Next
    INDEX
    Explanations

    superlative descriptors for size and magnitude in various contexts

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

    After "largest" or "oldest"

    np_acts-logits-general · gemini-2.0-flash

    largest, oldest, longest-running

    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
     آخر
    -0.36
     thousands
    -0.35
    وتی
    -0.35
    Various
    -0.34
     Scherer
    -0.33
     hundreds
    -0.32
     מיט
    -0.31
     became
    -0.31
    ulgação
    -0.30
     Lieblings
    -0.30
    POSITIVE LOGITS
     faſt
    0.92
     ſta
    0.90
     raiſ
    0.88
     ſtate
    0.86
     houſe
    0.84
     purpoſe
    0.82
     uſed
    0.81
    ſelf
    0.81
     poffible
    0.80
     ſtill
    0.79
    Activations Density 0.350%

    No Known Activations