© 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. 39-GEMMASCOPE-RES-16K
    6. 4120
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to political statements and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    告诉我
    -0.39
     dacht
    -0.37
     giggling
    -0.37
    帖最后由
    -0.37
     grinning
    -0.37
     whispering
    -0.37
    postIndex
    -0.35
     grinned
    -0.35
    Présentation
    -0.35
    }))
    
    -0.35
    POSITIVE LOGITS
     urge
    1.15
     Condem
    1.14
     condemn
    1.14
     appeal
    1.12
     urged
    1.11
     urges
    1.09
     condemned
    1.08
     appeals
    1.06
     urging
    1.05
     condemns
    1.05
    Activations Density 0.401%

    No Known Activations