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. 2-GEMMASCOPE-RES-16K
    6. 13113
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "affected" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HttpNotFound
    -0.57
    Personensuche
    -0.53
     formid
    -0.53
    Autoritní
    -0.50
    tually
    -0.49
     Madura
    -0.48
    LookAnd
    -0.48
     autorytatywna
    -0.47
    /**
    -0.47
    ✭✭
    -0.47
    POSITIVE LOGITS
     affected
    1.53
     Affected
    1.44
    Affected
    1.34
    affected
    1.28
     afectado
    1.00
     afectados
    0.96
     AFFECT
    0.95
     afectada
    0.91
     afectadas
    0.88
     affects
    0.79
    Activations Density 0.069%

    No Known Activations