© 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. 14621
    Prev
    Next
    INDEX
    Explanations

    components related to minimalist design and cozy atmospheres

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

    Followed by descriptive adjective

    np_acts-logits-general · gemini-2.0-flash

    unusual and original descriptions

    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
     ModelExpression
    -0.67
    apunov
    -0.65
     &___
    -0.56
    GIVEREF
    -0.52
    schuhe
    -0.52
     Downloader
    -0.51
    isRequired
    -0.51
    GroupLayout
    -0.50
     JADX
    -0.50
     jadx
    -0.49
    POSITIVE LOGITS
     inusual
    0.75
     ComVisible
    0.66
     unusual
    0.65
     ungewöhn
    0.59
    Bright
    0.58
     original
    0.58
    ########.
    0.57
     Unusual
    0.56
    Unusual
    0.56
    original
    0.55
    Activations Density 0.076%

    No Known Activations