© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9576
    Prev
    Next
    INDEX
    Explanations

    structured data representations or code snippets

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

    Code assignments and function definitions

    np_acts-logits-general · gemini-2.0-flash

    code structure and syntax

    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
     Ně
    -0.41
     Dünya
    -0.39
     yourselves
    -0.39
     noastre
    -0.39
    ….
    -0.38
    …..
    -0.38
    -“
    -0.38
    …”
    -0.38
     abbra
    -0.37
    …’
    -0.37
    POSITIVE LOGITS
    harusnya
    0.63
     bezeichneter
    0.62
    ORETICAL
    0.60
    MigrationBuilder
    0.59
     _
    0.59
     FontFamily
    0.59
     Default
    0.58
    cửa
    0.57
    sữa
    0.57
     Object
    0.57
    Activations Density 6.862%

    No Known Activations