© 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 EvalsExportsinterp-engineNEWAPI 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. 2914
    Prev
    Next
    INDEX
    Explanations

    references to database technology and its implications

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

    incidental or secondary information

    np_acts-logits-general · gemini-2.0-flash

    secondary or incidental

    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
     kaarangay
    -0.63
     فريبيس
    -0.52
     للاسماء
    -0.51
    OGND
    -0.51
    ArrowToggle
    -0.51
    ↹
    -0.50
    Personendaten
    -0.49
    Geplaatst
    -0.47
    Uninitialized
    -0.42
     отре
    -0.42
    POSITIVE LOGITS
     incidental
    0.90
     incidentally
    0.82
     secondary
    0.62
    ついで
    0.58
    顺便
    0.55
    Secondary
    0.55
     secondaire
    0.54
    たまたま
    0.54
    secondary
    0.52
     ancillary
    0.51
    Activations Density 0.467%

    No Known Activations