© 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. 2-GEMMASCOPE-RES-16K
    11. 8407
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.81
    __":
    -0.71
    __":
    -0.69
    tonsoft
    -0.68
     newOwner
    -0.64
    __':
    -0.64
    StoryboardSegue
    -0.63
    __':
    -0.63
    mtrl
    -0.63
    ToScroll
    -0.63
    POSITIVE LOGITS
     the
    0.75
    pazität
    0.60
    rån
    0.59
     with
    0.59
     dismissing
    0.55
    Polecam
    0.53
     treating
    0.53
    redirectTo
    0.53
     refute
    0.52
     بشأن
    0.52
    Activations Density 0.592%

    No Known Activations