© 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. 15-GEMMASCOPE-RES-16K
    11. 7765
    Prev
    Next
    INDEX
    Explanations

    phrases that denote comparison, particularly emphasizing the aspects of "best," "most," and "oldest" related to groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.74
    pyx
    -0.58
    Datuak
    -0.58
     مرئيه
    -0.55
     Othello
    -0.55
    IntoConstraints
    -0.54
     Limon
    -0.53
    Umb
    -0.53
     Hampstead
    -0.53
     peaches
    -0.53
    POSITIVE LOGITS
     all
    0.68
    WebServlet
    0.61
     amongst
    0.60
    стасия
    0.56
     bunch
    0.56
     możli
    0.54
    øst
    0.53
     among
    0.53
     doInBackground
    0.52
    possible
    0.52
    Activations Density 0.110%

    No Known Activations