© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 16116
    Prev
    Next
    INDEX
    Explanations

    references to Hollywood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     highlight
    -0.73
     incomplète
    -0.65
     highlights
    -0.65
     Highlight
    -0.64
    complexContent
    -0.63
     pleaſure
    -0.60
    ConstraintMaker
    -0.59
    highlights
    -0.59
    complish
    -0.58
     faptul
    -0.58
    POSITIVE LOGITS
     sc
    0.96
    Hollywood
    0.87
     laws
    0.84
     Laws
    0.83
     Hollywood
    0.82
     Sc
    0.74
    Laws
    0.72
     lazy
    0.71
     Lazy
    0.70
     LAWS
    0.69
    Activations Density 0.055%

    No Known Activations