© 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. 25-GEMMASCOPE-RES-16K
    6. 8908
    Prev
    Next
    INDEX
    Explanations

    texts focusing on themes of art and its representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGenerated
    -0.64
    wikk
    -0.58
    RunWith
    -0.54
    bollah
    -0.54
    rawDesc
    -0.53
     Bessel
    -0.53
    PRNewswire
    -0.53
    InjectAttribute
    -0.52
     Roskov
    -0.52
    antlr
    -0.50
    POSITIVE LOGITS
     oil
    0.76
     portraits
    0.70
     painted
    0.66
     scenes
    0.65
     landscapes
    0.65
     portrait
    0.64
     oils
    0.64
     scènes
    0.64
    oil
    0.64
     depictions
    0.63
    Activations Density 0.215%

    No Known Activations