© 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. 15-GEMMASCOPE-RES-16K
    6. 1848
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the concept of causation and consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organiser
    -0.72
     fevere
    -0.69
     Efq
    -0.68
     apparaître
    -0.68
     sweeps
    -0.65
     locaux
    -0.64
     OFDb
    -0.64
     heals
    -0.64
     extrapolated
    -0.63
     penetrates
    -0.63
    POSITIVE LOGITS
     being
    1.55
     getting
    1.40
     having
    1.38
     making
    1.34
     doing
    1.20
     taking
    1.16
     keeping
    1.11
     giving
    1.09
     providing
    1.06
     using
    1.05
    Activations Density 0.830%

    No Known Activations