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. 3148
    Prev
    Next
    INDEX
    Explanations

    features and components related to vehicle design and construction

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

    Refers to parts of objects

    np_acts-logits-general · gemini-2.0-flash

    parts of objects

    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
    évaluateur
    -0.75
     quæ
    -0.53
     validamos
    -0.53
     Instantiate
    -0.52
     institucional
    -0.52
    THON
    -0.51
    reportWebVitals
    -0.51
     tarko
    -0.50
     toothed
    -0.50
    deepEqual
    -0.49
    POSITIVE LOGITS
     area
    0.88
     region
    0.64
    area
    0.63
     виправивши
    0.61
     Area
    0.60
     AREA
    0.56
     AssemblyTitle
    0.54
    sbereich
    0.54
    DeleteBehavior
    0.54
    \{\\
    0.53
    Activations Density 0.743%

    No Known Activations