© 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. 8240
    Prev
    Next
    INDEX
    Explanations

    metrics related to clinical trial recruitment and adherence

    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
    #+#
    -0.65
    +#+#
    -0.61
     contextLoads
    -0.54
    Especially
    -0.52
    Alike
    -0.52
     prek
    -0.50
    łosi
    -0.49
     Especially
    -0.48
    ุทธ
    -0.48
    especially
    -0.47
    POSITIVE LOGITS
     multiplied
    1.33
     divided
    1.29
     minus
    1.24
     times
    1.14
    divided
    1.02
     subtracted
    0.96
    minus
    0.91
     plus
    0.90
     плюс
    0.88
     Divided
    0.85
    Activations Density 2.102%

    No Known Activations