© 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. 28-GEMMASCOPE-RES-16K
    6. 4861
    Prev
    Next
    INDEX
    Explanations

    technical concepts related to data structures and serialization in programming

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

    Dealing with arrays or lists

    np_acts-logits-general · gemini-2.0-flash

    array and collection concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.53
     AssemblyTitle
    -0.47
     yhte
    -0.44
    antwoorde
    -0.43
     lumineuse
    -0.42
    BASELINE
    -0.41
     invokingState
    -0.40
     larmes
    -0.40
    tangentMode
    -0.40
     lèvres
    -0.39
    POSITIVE LOGITS
     arrays
    0.93
     array
    0.91
     Array
    0.83
     collection
    0.82
     collections
    0.81
     Arrays
    0.75
     ARRAY
    0.71
    arrays
    0.70
    Array
    0.69
    array
    0.68
    Activations Density 1.272%

    No Known Activations