© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14538
    Prev
    Next
    INDEX
    Explanations

    abstract and mathematical concepts related to functions and properties in various contexts

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

    Mathematical or symbolic expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical and scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     p
    -1.19
    p
    -1.11
    p
    -1.02
     pn
    -0.98
    getP
    -0.97
     pa
    -0.96
     pp
    -0.96
     getP
    -0.96
     ps
    -0.93
     pname
    -0.93
    POSITIVE LOGITS
    chafft
    0.48
    chossen
    0.40
    chränk
    0.36
    chieben
    0.35
    mtrl
    0.35
    
    0.34
    maxcdn
    0.34
    ArgsConstructor
    0.33
    layui
    0.33
    fjspx
    0.33
    Activations Density 2.274%

    No Known Activations