© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5258
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and quantifications

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

    "Not" or alternatives ("or so", "if not") followed by approximate quantifiers

    np_acts-logits-general · gemini-2.0-flash

    quantities or ranges

    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
    PerformLayout
    -0.46
    ├──
    -0.42
    verifyException
    -0.40
    UrlEncoded
    -0.39
    VYMaps
    -0.38
     findAll
    -0.37
    ThemeOverlay
    -0.37
    !("{}",
    -0.36
    érience
    -0.36
     normalidad
    -0.36
    POSITIVE LOGITS
    Datuak
    0.56
     maybe
    0.51
    featureID
    0.48
    interopRequire
    0.47
    EndContext
    0.47
     perhaps
    0.45
     Chwiliwch
    0.44
    redos
    0.43
     hopefully
    0.42
     half
    0.42
    Activations Density 0.336%

    No Known Activations