© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1057
    Prev
    Next
    INDEX
    Explanations

    references to purpose and reasoning behind actions or stays

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "purpose" or "reason"

    np_acts-logits-general · gemini-2.0-flash

    reason why or purpose of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    PasswordEncoder
    -0.42
     calculées
    -0.34
    PrototypeOf
    -0.33
     mathematically
    -0.32
    beforeSend
    -0.31
    الإنجليزية
    -0.31
    forChild
    -0.30
    quiao
    -0.30
     صوتيه
    -0.30
     sartén
    -0.28
    POSITIVE LOGITS
     purpose
    1.62
    Purpose
    1.38
     PURPOSE
    1.36
     Purpose
    1.35
    目的
    1.31
    purpose
    1.30
     reason
    1.24
     purposes
    1.23
     tujuan
    1.19
    PURPOSE
    1.17
    Activations Density 0.520%

    No Known Activations