© 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. 128
    Prev
    Next
    INDEX
    Explanations

    keywords related to healthcare, social issues, and the impact of individual choices on wellbeing

    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
    Personensuche
    -0.61
    Viited
    -0.59
    think
    -0.58
    bitField
    -0.55
    Autoritní
    -0.55
    Vaata
    -0.54
     كورة
    -0.54
    первых
    -0.53
    toHaveBeenCalled
    -0.52
     Know
    -0.52
    POSITIVE LOGITS
     help
    1.50
     enable
    1.33
     allow
    1.26
     enhance
    1.17
    help
    1.16
     reduce
    1.13
     prevent
    1.10
     facilitate
    1.09
     increase
    1.09
     improve
    1.08
    Activations Density 1.298%

    No Known Activations