© 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. 1-GEMMASCOPE-RES-16K
    11. 14016
    Prev
    Next
    INDEX
    Explanations

    references to the "Home" page or section in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.06
    %)$
    -0.93
    NUMX
    -0.92
    ]")]
    -0.86
    RTSC
    -0.85
     Roskov
    -0.83
     $_"
    -0.83
     SDLK
    -0.82
    Grüsse
    -0.82
     themſelves
    -0.82
    POSITIVE LOGITS
     Home
    2.27
    Home
    2.18
    HOME
    1.51
    home
    1.44
     HOME
    1.36
     HOM
    1.08
    ホーム
    1.06
    HOM
    1.02
     Hom
    0.91
    Hom
    0.89
    Activations Density 0.119%

    No Known Activations