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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 14087
    Prev
    Next
    INDEX
    Explanations

    terms related to session management in programming

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

    Code snippets ending in punctuation/operators

    np_acts-logits-general · gemini-2.0-flash

    ember.js. code and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OCCURRED
    -0.73
     JADX
    -0.69
     snippetHide
    -0.68
    Diweddarwch
    -0.68
     localVar
    -0.64
    OrBuilder
    -0.63
     CGRectMake
    -0.62
     ब्रेकडाउन
    -0.62
    CGRectMake
    -0.60
    GEBURTSDATUM
    -0.60
    POSITIVE LOGITS
     Cake
    0.54
    cake
    0.47
     baker
    0.46
     baking
    0.46
     baked
    0.45
    ionato
    0.45
    Cake
    0.45
    sistor
    0.43
     Behaviors
    0.43
     vô
    0.43
    Activations Density 0.099%

    No Known Activations