© 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. 25-GEMMASCOPE-RES-16K
    11. 4517
    Prev
    Next
    INDEX
    Explanations

    concepts related to statistical modeling and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.73
    Fprintf
    -0.55
    ']>
    -0.52
     تعدى
    -0.51
    iecie
    -0.51
    TokenNameLBRACE
    -0.51
     kasarigan
    -0.50
     kaarangay
    -0.50
    strum
    -0.49
    =$?
    -0.49
    POSITIVE LOGITS
     constant
    0.88
     uniform
    0.85
     perfectly
    0.84
     homogeneous
    0.83
     pure
    0.76
     perfect
    0.73
     unchanging
    0.73
    constant
    0.72
     isotropic
    0.72
     homogenous
    0.71
    Activations Density 2.153%

    No Known Activations