Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14719
    Prev
    Next
    INDEX
    Explanations

    Java class and method structure, including visibility modifiers and declarations

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

    Followed by "public" or related words

    np_acts-logits-general · gemini-2.0-flash

    public static final

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    showthread
    -0.46
    懋
    -0.45
    Cry
    -0.42
    hugh
    -0.40
    flower
    -0.40
    cco
    -0.40
     Direkt
    -0.40
    fot
    -0.40
     dones
    -0.39
     surpris
    -0.39
    POSITIVE LOGITS
    public
    2.54
     public
    2.51
    Public
    1.75
     Public
    1.73
     PUBLIC
    1.69
     pública
    1.64
     público
    1.64
     publics
    1.58
    PUBLIC
    1.56
     pubblico
    1.54
    Activations Density 0.115%

    No Known Activations