© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 11524
    Prev
    Next
    INDEX
    Explanations

    the letter 'h' in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.70
    ak
    -0.64
    awtextra
    -0.62
     nakalista
    -0.62
    ah
    -0.51
    ou
    -0.51
    jupiter
    -0.50
    ap
    -0.49
    ſt
    -0.49
    Kanpo
    -0.48
    POSITIVE LOGITS
    MessageTagHelper
    0.55
    she
    0.53
    sent
    0.52
    ValueStyle
    0.52
    shi
    0.50
     كومونز
    0.50
    thâu
    0.49
    sensi
    0.49
    showroom
    0.49
    sal
    0.49
    Activations Density 0.135%

    No Known Activations