© 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. 2-GEMMASCOPE-RES-16K
    11. 558
    Prev
    Next
    INDEX
    Explanations

    terms related to adaptation or modifying something to suit conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     proceeding
    -0.45
    ClientRect
    -0.45
     imageNamed
    -0.43
     üzerinden
    -0.42
    Linki
    -0.41
    mybatisplus
    -0.41
     megsz
    -0.40
    ColumnHeaders
    -0.40
    ☚
    -0.39
    owano
    -0.39
    POSITIVE LOGITS
     adapt
    2.89
     adaptation
    2.66
     adapting
    2.64
     adapts
    2.58
     Adaptation
    2.47
     adapted
    2.45
     Adapt
    2.45
    adapt
    2.39
     adap
    2.36
    Adaptation
    2.36
    Activations Density 0.147%

    No Known Activations