© 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. 31-GEMMASCOPE-RES-16K
    11. 15198
    Prev
    Next
    INDEX
    Explanations

    phrases related to structural integrity and preservation

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

    words and phrases related to maintaining integrity or preserving the original state of something.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    phrases describing the preservation or retention of something intact despite changes or removals elsewhere.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ApiModelProperty
    -0.40
    AddHtmlAttribute
    -0.39
     Abs
    -0.37
     Bin
    -0.36
     irregular
    -0.35
     TextInputType
    -0.35
     abs
    -0.35
    不行
    -0.35
    setH
    -0.35
    かね
    -0.34
    POSITIVE LOGITS
     intact
    2.48
     undamaged
    1.76
     untouched
    1.61
     unharmed
    1.59
     unaltered
    1.55
     unchanged
    1.45
     integrity
    1.33
     unsc
    1.32
     undisturbed
    1.27
     inta
    1.27
    Activations Density 0.516%

    No Known Activations