© 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. 9-GEMMASCOPE-RES-16K
    6. 396
    Prev
    Next
    INDEX
    Explanations

    references to authors and their affiliations in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kuuta
    -0.60
     linkovi
    -0.56
    DeleteBehavior
    -0.56
    zeptember
    -0.54
    GEBURTSDATUM
    -0.52
    ServletException
    -0.52
     séances
    -0.51
    BagConstraints
    -0.51
     INFORMACIÓN
    -0.51
    appspot
    -0.50
    POSITIVE LOGITS
    PMailer
    0.61
     GenerationType
    0.53
     geweest
    0.52
    енча
    0.51
    tinyos
    0.49
    tagHelperRunner
    0.48
     désolés
    0.47
     ]
    
    0.47
     GoogleFonts
    0.47
    LinkId
    0.46
    Activations Density 0.452%

    No Known Activations