© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10767
    Prev
    Next
    INDEX
    Explanations

    references to negative aspects or outcomes

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

    Following "negative"

    np_acts-logits-general · gemini-2.0-flash

    negative impact or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upol
    -0.57
     Accord
    -0.56
    ernalia
    -0.55
    bloom
    -0.53
     Référence
    -0.52
    ┱
    -0.51
    Jîn
    -0.50
    ANSA
    -0.50
    PageFactory
    -0.50
    ualla
    -0.49
    POSITIVE LOGITS
     negative
    1.13
     negativo
    0.98
    Negative
    0.95
    negative
    0.93
     négatif
    0.92
     Negative
    0.91
     negativ
    0.90
     negativos
    0.87
     negatively
    0.86
     NEGATIVE
    0.85
    Activations Density 0.885%

    No Known Activations