© 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. 2-GEMMASCOPE-RES-16K
    11. 8692
    Prev
    Next
    INDEX
    Explanations

    phrases that denote reasons or justifications for events or actions

    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
    AndEndTag
    -0.47
    izr
    -0.46
    endphp
    -0.43
     Planung
    -0.41
     setOpen
    -0.40
    서는
    -0.40
    bersicht
    -0.40
    FXMLLoader
    -0.40
     opening
    -0.39
    didSet
    -0.39
    POSITIVE LOGITS
     responsible
    0.61
    responsible
    0.61
     responsable
    0.57
     responsável
    0.54
     responsáveis
    0.53
     Responsible
    0.51
     verantwortlich
    0.51
    Responsible
    0.49
    负责
    0.48
     responsibility
    0.47
    Activations Density 0.308%

    No Known Activations