© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 337
    Prev
    Next
    INDEX
    Explanations

    emotions and feelings expressed in various contexts

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

    following comparative adjectives

    np_acts-logits-general · gemini-2.0-flash

    more followed by descriptors

    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
     anniversaire
    -0.42
     avoient
    -0.34
     getItemId
    -0.31
     potest
    -0.31
     darbo
    -0.30
     verwan
    -0.30
    ItemId
    -0.30
     trận
    -0.30
     cauſe
    -0.30
     změ
    -0.29
    POSITIVE LOGITS
    extAlignment
    0.66
    ImageContext
    0.65
    DockStyle
    0.65
     silvery
    0.63
     otomatig
    0.60
     ujednoznacz
    0.59
     reminiscent
    0.58
    InjectAttribute
    0.58
     distinctly
    0.58
     airy
    0.57
    Activations Density 0.186%

    No Known Activations