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. 25-GEMMASCOPE-RES-16K
    6. 8074
    Prev
    Next
    INDEX
    Explanations

    conditional clauses and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    YOU
    -1.75
    your
    -1.58
    Your
    -1.48
     YOU
    -1.46
    you
    -1.44
    YOUR
    -1.41
    You
    -1.39
     You
    -1.39
    yourself
    -1.36
     Yourself
    -1.32
    POSITIVE LOGITS
     autorytatywna
    0.71
     referenties
    0.69
    原始内容存档于
    0.59
     jsPsych
    0.59
     跳转至
    0.59
     >=",
    0.57
    Билгалдахарш
    0.56
    期刊论文
    0.54
    __(/*!
    0.54
    Pictured
    0.52
    Activations Density 0.200%

    No Known Activations