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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13153
    Prev
    Next
    INDEX
    Explanations

    symbols indicating comparisons or greater-than relationships

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

    Greater-than sign

    np_acts-logits-general · gemini-2.0-flash

    `>` followed by code or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     которая
    -0.44
    JsonInclude
    -0.41
    chale
    -0.41
     dispozici
    -0.40
    setcounter
    -0.40
    Fc
    -0.37
     itſelf
    -0.37
     araw
    -0.36
    いぐるみ
    -0.36
     referrerpolicy
    -0.36
    POSITIVE LOGITS
     >
    1.09
    >>>
    0.96
    >>>>
    0.92
    displayquote
    0.90
    >>>>>>
    0.89
     >>
    0.85
    >>>>>
    0.85
     >>=
    0.84
    >>>>>>>>
    0.84
     $>
    0.83
    Activations Density 0.284%

    No Known Activations