© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1405
    Prev
    Next
    INDEX
    Explanations

    the word "tie" and related concepts, particularly in a context of connection or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    الحياه
    -0.52
    meant
    -0.51
    MigrationBuilder
    -0.46
    WithIOException
    -0.46
    chosen
    -0.44
     MainAxisSize
    -0.44
    ########.
    -0.43
    commitment
    -0.42
     snippetHide
    -0.42
    fortunately
    -0.41
    POSITIVE LOGITS
    Interface
    1.11
     Interface
    0.68
    interface
    0.66
     tie
    0.63
    INTERFACE
    0.59
    Interfaces
    0.58
    Tie
    0.57
     interface
    0.56
     Tie
    0.54
    interfaces
    0.53
    Activations Density 0.084%

    No Known Activations