© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3512
    Prev
    Next
    INDEX
    Explanations

    repeated use of the word "because" indicating reasoning or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "because"

    np_acts-logits-general · gemini-2.0-flash

    introduces a reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LLocation
    -0.41
     teatral
    -0.41
     scén
    -0.40
    Heer
    -0.40
    fld
    -0.40
     gesamten
    -0.40
     hvit
    -0.40
    ing
    -0.40
     toalha
    -0.39
     vorliegenden
    -0.39
    POSITIVE LOGITS
    because
    1.30
    ECAUSE
    1.26
     BECAUSE
    1.21
    Because
    1.19
     Because
    1.18
     because
    1.16
    porque
    1.09
    Porque
    1.05
     Porque
    1.05
     porque
    1.00
    Activations Density 0.114%

    No Known Activations