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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53336
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in texts

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

    Spanish addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.96
    SequentialGroup
    -0.93
    RenderAtEndOf
    -0.87
     cherchés
    -0.87
     مشين
    -0.86
    Hozzáférés
    -0.85
    webElementXpaths
    -0.84
    脚注の使い方
    -0.83
    #+#
    -0.78
     '\\;'
    -0.78
    POSITIVE LOGITS
     getAge
    0.45
     lulus
    0.42
     registered
    0.40
     persone
    0.39
     direcciones
    0.38
     subpoena
    0.38
     dirección
    0.38
    ged
    0.38
    Dirección
    0.38
     privateKey
    0.38
    Activations Density 0.010%

    No Known Activations