© 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. 18-GEMMASCOPE-RES-16K
    6. 7991
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in numerical data or code

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

    "Int64" or "uint32/64"

    np_acts-logits-general · gemini-2.0-flash

    integer types and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.53
     Allgemeinen
    -0.51
    ,
    -0.49
     państw
    -0.47
     spalle
    -0.45
     passare
    -0.45
     doccia
    -0.45
    /
    -0.43
     cardíaca
    -0.43
     isolé
    -0.43
    POSITIVE LOGITS
    ########.
    1.12
    ]--;
    0.89
     виправивши
    0.89
     CreateTagHelper
    0.89
    LookAnd
    0.85
    neſs
    0.85
     المعيارى
    0.85
    ^(@)
    0.84
    setVerticalGroup
    0.84
     ModelExpression
    0.84
    Activations Density 0.129%

    No Known Activations