© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 581
    Prev
    Next
    INDEX
    Explanations

    phrases indicating health risks and complications related to medical procedures and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows prepositions or subordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     libremente
    -0.32
     mediodía
    -0.30
     cuchara
    -0.30
     supuestamente
    -0.27
    อ้างอิง
    -0.27
     Summe
    -0.27
     fixé
    -0.27
     tercio
    -0.27
    aksana
    -0.26
     recuperação
    -0.26
    POSITIVE LOGITS
    MessageTagHelper
    0.69
     difficulties
    0.65
     violations
    0.64
     rashes
    0.64
    !*\
    0.62
     errors
    0.60
    SequentialGroup
    0.60
     fraud
    0.60
     loss
    0.59
     disasters
    0.59
    Activations Density 1.083%

    No Known Activations