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. 5-GEMMASCOPE-RES-16K
    6. 8722
    Prev
    Next
    INDEX
    Explanations

    lines that contain parameter definitions and their respective values in code or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.57
    _
    -0.54
     t
    -0.54
      
    -0.53
     de
    -0.50
    -
    -0.50
     my
    -0.49
     y
    -0.48
     f
    -0.47
     i
    -0.47
    POSITIVE LOGITS
     myſelf
    1.32
     purpoſe
    1.30
     itſelf
    1.27
     raiſ
    1.21
    ^(@)
    1.20
    ſelves
    1.17
    WebVitals
    1.15
     مشين
    1.15
    ſelf
    1.15
     doubtnut
    1.12
    Activations Density 0.091%

    No Known Activations