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. 18-GEMMASCOPE-RES-16K
    6. 3673
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and identifiers, often associated with data or code

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

    Hexadecimal strings

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings

    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
     betweenstory
    -0.73
     itſelf
    -0.69
    Diwedd
    -0.68
     CreateTagHelper
    -0.67
    ñora
    -0.67
    脚注の使い方
    -0.66
     StatefulWidget
    -0.65
     Sardin
    -0.63
     $_"
    -0.63
     RCS
    -0.63
    POSITIVE LOGITS
    ,
    0.50
     
    0.46
    .
    0.45
    afficheront
    0.45
     holding
    0.45
    SpringBootTest
    0.44
    vensko
    0.43
    isLoaded
    0.43
     And
    0.42
    cloudfront
    0.42
    Activations Density 0.076%

    No Known Activations