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. 22-GEMMASCOPE-RES-16K
    6. 8000
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

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

    Follows a sentence or clause

    np_acts-logits-general · gemini-2.0-flash

    case, the, core, materials, NC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.33
     ་་
    -1.29
     ―――――
    -1.24
    >\<^
    -1.23
    NUMX
    -1.22
    \<^
    -1.20
    ſelves
    -1.15
     GenerationType
    -1.13
    ressee
    -1.10
     Forumite
    -1.09
    POSITIVE LOGITS
    <eos>
    1.53
    ↵
    1.06
     
    0.99
    .
    0.97
    The
    0.93
     I
    0.91
      
    0.89
    ↵↵
    0.89
    I
    0.89
    We
    0.88
    Activations Density 0.410%

    No Known Activations