© 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. 5427
    Prev
    Next
    INDEX
    Explanations

    references to understanding or defining purpose in life

    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
    runApp
    -0.54
    ilanth
    -0.53
    المشاركات
    -0.52
    nologue
    -0.52
    UseVisualStyle
    -0.50
    izoen
    -0.49
    ativement
    -0.49
    Portale
    -0.48
    MessageOf
    -0.47
     Италијани
    -0.47
    POSITIVE LOGITS
     confusion
    1.96
     confusing
    1.92
     confused
    1.83
     confuse
    1.70
     Confusion
    1.68
    Confused
    1.67
     confuses
    1.67
     confuso
    1.61
    Confusion
    1.61
     Confused
    1.56
    Activations Density 0.746%

    No Known Activations