© 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. 8989
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that suggest preference or alternatives

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

    "rather than"

    np_acts-logits-general · gemini-2.0-flash

    rather than

    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
    astify
    -0.48
     camb
    -0.39
    AndroidJUnit
    -0.39
    toPromise
    -0.38
     Jennie
    -0.37
    ‟
    -0.37
     Reverso
    -0.37
     gros
    -0.35
     cip
    -0.35
     UCS
    -0.35
    POSITIVE LOGITS
     necesariamente
    0.73
     necessarily
    0.69
     nécessairement
    0.66
     necessariamente
    0.65
     quelcon
    0.62
    それとも
    0.60
    necessarily
    0.59
     isolada
    0.58
     pouvoit
    0.58
     justru
    0.57
    Activations Density 0.273%

    No Known Activations