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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15503
    Prev
    Next
    INDEX
    Explanations

    text related to software licenses and their terms

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

    Code comments' delimiters

    np_acts-logits-general · gemini-2.0-flash

    code comments and diff markers

    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
    addPreferredGap
    -0.58
    ;—
    -0.51
     ChromeDriver
    -0.51
    InputTagHelper
    -0.50
    bidi
    -0.48
    JsonFormat
    -0.48
    canestro
    -0.48
    ){$
    -0.48
     그는
    -0.47
    EqualsAnd
    -0.47
    POSITIVE LOGITS
    #+#
    1.49
    +#+
    1.34
    +:+
    0.98
    ########.
    0.97
    :+:
    0.97
    +#+#
    0.91
     فريبيس
    0.71
    
    0.63
    出版年
    0.62
    uxxxx
    0.58
    Activations Density 0.098%

    No Known Activations