Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10409
    Prev
    Next
    INDEX
    Explanations

    words related to realization and optimization processes

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

    ending in "ise", "isation", "ised", or "isation"

    np_acts-logits-general · gemini-2.0-flash

    -ised, -isation, -ation, -al suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ее
    -1.25
    Еще
    -1.19
    Theater
    -1.16
     theater
    -1.15
     tumors
    -1.13
     theaters
    -1.11
    ighborhood
    -1.10
     Еще
    -1.08
     Tumors
    -1.08
    ьез
    -1.08
    POSITIVE LOGITS
     şi
    1.74
    Ещё
    1.69
     organisations
    1.65
     generalised
    1.63
     organisational
    1.63
     utilisation
    1.63
     characterised
    1.59
     unauthorised
    1.58
     Şi
    1.57
    Colours
    1.56
    Activations Density 0.351%

    No Known Activations