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. 20-GEMMASCOPE-RES-16K
    6. 5265
    Prev
    Next
    INDEX
    Explanations

    terms related to organized entities or structures

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

    "organization" or "organised"

    np_acts-logits-general · gemini-2.0-flash

    organized entities and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.80
    rrggbb
    -0.70
    swagger
    -0.67
    CodeAttribute
    -0.65
    oluene
    -0.65
     Nok
    -0.65
    Geographie
    -0.65
    НИК
    -0.64
     fallait
    -0.64
     Sita
    -0.63
    POSITIVE LOGITS
    ally
    0.85
     structure
    0.69
    alised
    0.65
     struct
    0.60
    ALLY
    0.59
     organis
    0.59
     Structure
    0.56
    structure
    0.55
     organisations
    0.54
    </b>
    0.54
    Activations Density 0.101%

    No Known Activations