© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 6670
    Prev
    Next
    INDEX
    Explanations

    references to adaptations of media, specifically those that have been modified from one format to another, such as plays or films

    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
    RunWith
    -0.70
    +#+
    -0.65
    })));
    -0.64
    IsContent
    -0.60
    Cyfeiriadau
    -0.54
    itinéraire
    -0.53
    ContentAlignment
    -0.53
    GenerationType
    -0.52
     EClass
    -0.52
     HasFactory
    -0.52
    POSITIVE LOGITS
     television
    1.00
     TV
    0.95
     radio
    0.88
     tv
    0.83
     motion
    0.81
     feature
    0.78
    television
    0.74
     web
    0.74
     audiobook
    0.73
     stage
    0.73
    Activations Density 0.485%

    No Known Activations