© 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 EvalsExportsAPI 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. 734
    Prev
    Next
    INDEX
    Explanations

    code related to testing and debugging methods within programming contexts

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

    Code, paths, and context variables

    np_acts-logits-general · gemini-2.0-flash

    we have, are unwilling

    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
     HttpNotFound
    -0.49
     ſie
    -0.45
    enterOuterAlt
    -0.44
     AssemblyCompany
    -0.44
    stdc
    -0.42
     ſon
    -0.40
    unjung
    -0.40
     ainfi
    -0.40
     Reſ
    -0.40
     JNI
    -0.39
    POSITIVE LOGITS
     يتيمه
    0.65
     jadx
    0.52
    Personendaten
    0.45
    ⤹
    0.45
    OGND
    0.44
    WithIOException
    0.44
    ёх
    0.40
     للاسماء
    0.40
    grà
    0.38
    GTCX
    0.38
    Activations Density 0.193%

    No Known Activations