© 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. 9869
    Prev
    Next
    INDEX
    Explanations

    special formatting or unique characters in the text

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

    Code or non-English terms

    np_acts-logits-general · gemini-2.0-flash

    pending Intent or limited extent

    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
    tagHelperRunner
    -0.61
    RegressionTest
    -0.51
     nî
    -0.49
    RTLI
    -0.48
    WebElementEntity
    -0.48
    haikusbot
    -0.48
     ProtoMessage
    -0.47
     للمعارف
    -0.44
    hematical
    -0.42
     كومونز
    -0.42
    POSITIVE LOGITS
     GenerationType
    0.52
    principalTable
    0.48
     Audiodateien
    0.47
     noDo
    0.41
     виправивши
    0.40
    complexContent
    0.40
    "}}
    0.40
     wszystkim
    0.40
    occasione
    0.40
     ModelExpression
    0.39
    Activations Density 0.700%

    No Known Activations