© 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. 309
    Prev
    Next
    INDEX
    Explanations

    references to legal and administrative processes related to governance

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

    preceding past tense verbs

    np_acts-logits-general · gemini-2.0-flash

    subsequently became

    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
    LEncoder
    -0.51
    NameInMap
    -0.48
     allAfrica
    -0.46
    ItemBackground
    -0.46
    rdida
    -0.45
    Personendaten
    -0.44
    lorette
    -0.44
     devraient
    -0.44
    podr
    -0.44
    Possible
    -0.43
    POSITIVE LOGITS
     became
    0.84
     subsequently
    0.75
     eventually
    0.69
    后来
    0.69
     Subsequently
    0.67
    became
    0.66
    当时
    0.66
    當時
    0.66
    今では
    0.65
     later
    0.63
    Activations Density 1.106%

    No Known Activations