Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14879
    Prev
    Next
    INDEX
    Explanations

    information regarding health risks and preventive measures related to medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.42
    SharedDtor
    -0.42
    onView
    -0.41
     intStringLen
    -0.40
     Hump
    -0.40
     NSCoder
    -0.40
     ModelRenderer
    -0.39
     يتيمه
    -0.38
    flage
    -0.38
    ikala
    -0.38
    POSITIVE LOGITS
     risk
    0.65
    risk
    0.59
     Risiken
    0.56
     Gefähr
    0.56
    Risk
    0.55
     Risk
    0.55
     risks
    0.55
     safety
    0.54
     safer
    0.53
     Sicherheits
    0.53
    Activations Density 0.446%

    No Known Activations