© 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. 14586
    Prev
    Next
    INDEX
    Explanations

    references to fixed or stable concepts in various contexts, particularly in relation to measurements or parameters

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

    "fixed" and its subsequent words

    np_acts-logits-general · gemini-2.0-flash

    fixed followed by terms

    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
     TAMBÉM
    -0.65
     Mucha
    -0.59
    ^@
    -0.59
     Efq
    -0.52
    ----</
    -0.52
    oa̍t
    -0.51
     JNI
    -0.51
     NSError
    -0.51
    jekk
    -0.51
     qualifié
    -0.50
    POSITIVE LOGITS
     income
    0.55
    income
    0.55
    xed
    0.54
    AndEndTag
    0.54
    InjectAttribute
    0.54
     abode
    0.53
    ity
    0.53
     rate
    0.52
     AssemblyCulture
    0.52
    GeneratedValue
    0.51
    Activations Density 0.158%

    No Known Activations