© 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. 263
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and their associations

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

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    INS cannot detain

    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
     صوتيه
    -0.72
    Tikang
    -0.61
    xase
    -0.59
    PerformLayout
    -0.59
     NSCoder
    -0.57
    delwed
    -0.57
    tagHelperRunner
    -0.56
     DBNull
    -0.55
    __(/*!
    -0.54
     defaultstate
    -0.54
    POSITIVE LOGITS
    uller
    0.44
    apt
    0.44
    mann
    0.42
    akt
    0.40
    tell
    0.40
    aff
    0.40
    ilan
    0.40
    odyne
    0.39
    iglio
    0.39
     Uptake
    0.38
    Activations Density 4.075%

    No Known Activations