© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4253
    Prev
    Next
    INDEX
    Explanations

    calls for action or suggestions for improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "just"

    np_acts-logits-general · gemini-2.0-flash

    just followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.48
     ennen
    -0.45
    WriteBarrier
    -0.44
    httphttps
    -0.44
     inden
    -0.44
    новниш
    -0.43
     Before
    -0.42
    Trayectoria
    -0.41
    لیس
    -0.41
    :]:
    -0.41
    POSITIVE LOGITS
    干脆
    0.79
     outright
    0.75
     LUMP
    0.69
     gewoon
    0.69
    astify
    0.65
    Portail
    0.64
     Просто
    0.64
     einfach
    0.62
     straightforward
    0.59
    DataSetChanged
    0.59
    Activations Density 0.224%

    No Known Activations