© 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. 5-GEMMASCOPE-RES-16K
    11. 6032
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.74
    UnusedPrivate
    -0.68
    İstinadlar
    -0.68
    principalTable
    -0.67
    GenerationType
    -0.64
    PerformLayout
    -0.64
    velopes
    -0.63
    ensement
    -0.61
    nocześnie
    -0.60
     Superhosts
    -0.59
    POSITIVE LOGITS
    To
    1.56
     To
    1.47
     Toh
    0.97
     Чтобы
    0.95
     TO
    0.94
    TO
    0.92
     Để
    0.85
    为了
    0.84
    Чтобы
    0.84
    For
    0.74
    Activations Density 0.140%

    No Known Activations