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. 18-GEMMASCOPE-RES-16K
    6. 14460
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and their citations

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

    City or location name

    np_acts-logits-general · gemini-2.0-flash

    place names in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    らし
    -0.44
     chemists
    -0.43
    이
    -0.41
    vi
    -0.40
     ma
    -0.36
     Anglais
    -0.36
     mix
    -0.36
     Acerca
    -0.36
    さん
    -0.35
    mage
    -0.35
    POSITIVE LOGITS
    #+#
    0.96
     autorytatywna
    0.94
     ويكيپيديا
    0.93
    ValueStyle
    0.90
    GraphicsUnit
    0.89
     Италијани
    0.87
    évaluateur
    0.86
    CloseOperation
    0.86
    RectangleBorder
    0.85
    localctx
    0.84
    Activations Density 0.104%

    No Known Activations