© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27-GEMMASCOPE-RES-16K
    11. 9656
    Prev
    Next
    INDEX
    Explanations

    concepts related to fragility and preservation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.56
     stump
    -0.43
    orthand
    -0.42
    عرِّف
    -0.41
     CallOverrides
    -0.41
     TextAppearance
    -0.40
    entrion
    -0.40
    émission
    -0.40
     paisagem
    -0.40
    ExecuteReader
    -0.39
    POSITIVE LOGITS
     fragile
    1.88
     frág
    1.55
     fragility
    1.54
     delicate
    1.38
     vulnerable
    1.32
    脆弱
    1.30
     sensitive
    1.16
     frail
    1.13
     brittle
    1.09
     delicado
    1.05
    Activations Density 0.436%

    No Known Activations