© 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. 5-GEMMASCOPE-RES-16K
    11. 5141
    Prev
    Next
    INDEX
    Explanations

    quoted strings and their formatting details in code or data schemas

    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
     Efq
    -1.35
    ſelves
    -1.30
     فريبيس
    -1.25
    )";
    -1.25
    .")
    -1.23
    ."</
    -1.22
     itſelf
    -1.20
     $_"
    -1.19
     myſelf
    -1.19
    ſelf
    -1.18
    POSITIVE LOGITS
     "
    0.86
     “
    0.86
    :
    0.79
    ="
    0.75
    =
    0.74
     (
    0.72
     =
    0.70
     :
    0.67
     '
    0.63
     
    0.63
    Activations Density 0.168%

    No Known Activations