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. 24-GEMMASCOPE-RES-16K
    6. 4449
    Prev
    Next
    INDEX
    Explanations

    references to properties, housing, governmental actions, legal cases, and evidence of wrongdoing

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

    "including" and what follows it

    np_acts-logits-general · gemini-2.0-flash

    introducing lists

    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
     gì
    -0.48
     względu
    -0.48
    처럼
    -0.46
    ❮
    -0.44
     ||
    
    -0.44
    esseract
    -0.44
    Autre
    -0.43
    orced
    -0.43
    llary
    -0.42
    TextAppearance
    -0.42
    POSITIVE LOGITS
     including
    3.09
    including
    2.60
     Including
    2.60
    Including
    2.55
     incluindo
    2.30
     INCLUDING
    2.27
     incluyendo
    2.21
     waaronder
    2.17
     включая
    2.05
    INCLUDING
    2.00
    Activations Density 0.720%

    No Known Activations