© 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. 17-GEMMASCOPE-RES-16K
    6. 9492
    Prev
    Next
    INDEX
    Explanations

    references to media and its coverage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artement
    -0.51
     vad
    -0.50
    (!__
    -0.49
    ighth
    -0.48
     Pickett
    -0.45
    nze
    -0.43
     utr
    -0.43
    sick
    -0.43
    Exhibit
    -0.43
    Démographie
    -0.42
    POSITIVE LOGITS
     media
    1.05
     MEDIA
    1.01
     Media
    0.97
     medias
    0.95
    MEDIA
    0.91
     Medien
    0.87
     mídia
    0.85
    media
    0.84
     outlets
    0.84
    Media
    0.80
    Activations Density 0.095%

    No Known Activations