© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 4781
    Prev
    Next
    INDEX
    Explanations

    the letter 'z' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzzz
    -0.56
    zz
    -0.52
    zzz
    -0.46
    да
    -0.44
    illa
    -0.42
    Personendaten
    -0.42
    mstyle
    -0.42
    zura
    -0.41
    tagHelperRunner
    -0.40
    zy
    -0.40
    POSITIVE LOGITS
    song
    0.49
    sand
    0.48
    ship
    0.47
    sz
    0.46
    ska
    0.45
    soft
    0.45
    shop
    0.44
    sr
    0.44
    say
    0.44
    ske
    0.44
    Activations Density 0.157%

    No Known Activations