© 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. 24-GEMMASCOPE-RES-16K
    11. 5042
    Prev
    Next
    INDEX
    Explanations

    themes of conflict and survival in dystopian settings

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

    danger and mystery

    np_acts-logits-general · gemini-2.0-flash

    danger and mystery

    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
     Италијани
    -0.72
     disambiguazione
    -0.58
    Havolalar
    -0.57
     tartalomajánló
    -0.54
     validamos
    -0.52
    oredCriteria
    -0.52
    \{\\
    -0.51
    TypedDataSet
    -0.49
     ujednoznacz
    -0.49
     morrow
    -0.48
    POSITIVE LOGITS
     inesper
    0.44
     mysterious
    0.41
     suddenly
    0.41
     ontdek
    0.40
     dangerously
    0.40
     gefährlich
    0.40
     mysteriously
    0.39
     rahasia
    0.39
     plötzlich
    0.38
     tajem
    0.38
    Activations Density 0.377%

    No Known Activations