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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 4667
    Prev
    Next
    INDEX
    Explanations

    words that indicate agreement, concession, or logical consequence, such as "allows", "agree", "therefore", "however", and "accordingly".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @dextersjab

    sentence starters and transitional phrases that indicate progression or sequence in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.38
    ff
    -0.32
    jeta
    -0.31
    ffar
    -0.31
    <bos>
    -0.31
     חיצוניים
    -0.31
    pri
    -0.30
    pe
    -0.30
    λοι
    -0.30
    te
    -0.30
    POSITIVE LOGITS
     Theſe
    0.52
     becauſe
    0.49
     myſelf
    0.46
    AddTagHelper
    0.45
     виправивши
    0.44
     فريبيس
    0.43
     Мексичка
    0.43
    expandindo
    0.40
     Jefus
    0.40
     ſeveral
    0.40
    Activations Density 0.789%

    No Known Activations