© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 4954
    Prev
    Next
    INDEX
    Explanations

    discussions about measurement scales and their reliability in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apnews
    -0.57
    ibouti
    -0.51
    ActivityCompat
    -0.51
    subequations
    -0.49
     ioutil
    -0.49
     nahilalakip
    -0.48
    DialogContent
    -0.48
    ropolitan
    -0.48
     좋은
    -0.48
    hObject
    -0.47
    POSITIVE LOGITS
     scale
    5.09
     Scale
    4.75
    scale
    4.43
    Scale
    4.41
     SCALE
    4.26
     scales
    4.18
    SCALE
    3.70
     Scales
    3.70
    scales
    3.43
     scaled
    3.38
    Activations Density 0.068%

    No Known Activations