© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2194
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases that introduce possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences starting with "If"

    np_acts-logits-general · gemini-2.0-flash

    if clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ยม
    -0.39
     <>",
    -0.39
    UVWXYZ
    -0.39
    商
    -0.38
     Administrativna
    -0.38
    ahua
    -0.37
    endregion
    -0.37
    lera
    -0.37
    rungsseite
    -0.36
    存于互联网档案馆
    -0.36
    POSITIVE LOGITS
    หาก
    0.56
     If
    0.51
    If
    0.49
     étoient
    0.46
    ModelSerializer
    0.44
    Якщо
    0.43
    pozdrawiam
    0.42
     avoient
    0.41
     hadn
    0.41
     Nếu
    0.40
    Activations Density 0.258%

    No Known Activations