© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1811
    Prev
    Next
    INDEX
    Explanations

    terms related to ions and their properties

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

    Follows "called", "as", or "known as"

    np_acts-logits-general · gemini-2.0-flash

    introducing named items

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     doubtnut
    -0.67
    contentLoaded
    -0.61
     myſelf
    -0.60
     Efq
    -0.59
    "},
    -0.57
     AspNetCore
    -0.57
    MessageTagHelper
    -0.56
    nościo
    -0.56
     ―――――
    -0.56
    ilarities
    -0.56
    POSITIVE LOGITS
     sogenannte
    1.06
     sogenannten
    1.03
     called
    0.99
    called
    0.94
     sogen
    0.82
     tzw
    0.78
     termed
    0.78
    叫做
    0.76
    所谓的
    0.72
     называется
    0.71
    Activations Density 0.605%

    No Known Activations