© 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. 33-GEMMASCOPE-RES-16K
    6. 763
    Prev
    Next
    INDEX
    Explanations

    critical elements related to tension, conflict, and significant events in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.41
     являются
    -0.37
    copyWith
    -0.36
    Kaieteur
    -0.33
     whofe
    -0.32
     defStyleAttr
    -0.32
    ArgsConstructor
    -0.32
    KindOfClass
    -0.31
    Were
    -0.31
    missing
    -0.31
    POSITIVE LOGITS
    存于互联网档案馆
    0.54
     tartalomajánló
    0.54
    iseks
    0.51
     egens
    0.50
     utafitiHapana
    0.50
     stays
    0.49
     progresses
    0.49
     proceeds
    0.49
    frå
    0.49
    WriteTagHelper
    0.47
    Activations Density 0.943%

    No Known Activations