© 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. 7-GEMMASCOPE-RES-16K
    11. 14168
    Prev
    Next
    INDEX
    Explanations

    the word "almost" and its variations to identify levels of approximation or near-completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.64
     AssemblyCulture
    -0.59
     Lors
    -0.45
     ayrıca
    -0.45
     PDC
    -0.44
    SharedDtor
    -0.44
     Thebes
    -0.44
    PDC
    -0.43
    uinal
    -0.43
     HasFactory
    -0.43
    POSITIVE LOGITS
     almost
    2.22
     Almost
    2.16
    Almost
    2.13
    almost
    1.94
     nearly
    1.73
     quase
    1.65
     presque
    1.63
     Nearly
    1.57
     почти
    1.55
     casi
    1.53
    Activations Density 0.084%

    No Known Activations