© 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. 21-GEMMASCOPE-RES-16K
    11. 13238
    Prev
    Next
    INDEX
    Explanations

    expressions of concern and the desire for connection in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     châ
    -0.53
     __
    -0.52
     queſta
    -0.50
    iſen
    -0.50
    /***/
    -0.50
    WithMany
    -0.49
    iffance
    -0.49
    AsStream
    -0.49
     prioritise
    -0.48
     Houſe
    -0.47
    POSITIVE LOGITS
    ConstraintMaker
    0.44
     paraître
    0.40
    meanor
    0.35
     metá
    0.34
     Yeah
    0.33
     Yes
    0.32
     vêtement
    0.32
    transQ
    0.32
     препратки
    0.31
     secuencia
    0.31
    Activations Density 0.172%

    No Known Activations