© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11196
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss accountability and consequences in political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.58
    DataPropertyName
    -0.49
    المناصب
    -0.46
    好不容易
    -0.43
    tagHelperRunner
    -0.41
    BufferException
    -0.40
    typeorm
    -0.40
     contener
    -0.40
     apasion
    -0.38
    /******/
    -0.38
    POSITIVE LOGITS
     automaticamente
    0.78
     automatically
    0.78
     автоматически
    0.70
     thereby
    0.70
     essentially
    0.70
     effectively
    0.70
     automáticamente
    0.69
     automatiquement
    0.68
     indirectly
    0.67
     Effectively
    0.65
    Activations Density 0.623%

    No Known Activations