© 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. 2199
    Prev
    Next
    INDEX
    Explanations

    references to personal memories and experiences

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

    Past tense or time-related words

    np_acts-logits-general · gemini-2.0-flash

    past/formerly

    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
     nahilalakip
    -0.62
    saraba
    -0.60
     GenerationType
    -0.59
    ſelben
    -0.57
     ReactDOM
    -0.56
    TagMode
    -0.55
     nakalista
    -0.54
    دانشنامهٔ
    -0.54
     Réponses
    -0.54
    ⭗
    -0.53
    POSITIVE LOGITS
     vroeger
    1.60
     autrefois
    1.45
     kiedyś
    1.39
     früher
    1.38
    昔
    1.23
    当年
    1.16
    かつて
    1.15
     formerly
    1.15
     einst
    1.10
     olden
    1.07
    Activations Density 0.743%

    No Known Activations