© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10104
    Prev
    Next
    INDEX
    Explanations

    references to groups or parties involved in legal cases, particularly focusing on their roles and claims

    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
     udah
    -0.59
    ритори
    -0.59
     himo
    -0.56
     Familienname
    -0.55
     الحره
    -0.54
     sumpay
    -0.52
     препратки
    -0.52
    rungsseite
    -0.51
    adaptiveStyles
    -0.50
    Reminds
    -0.50
    POSITIVE LOGITS
     does
    2.00
     did
    1.62
    does
    1.57
     do
    1.57
     cannot
    1.43
     neither
    1.43
     doesn
    1.36
     doesnt
    1.26
     Neither
    1.25
     Does
    1.25
    Activations Density 1.794%

    No Known Activations