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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 5949
    Prev
    Next
    INDEX
    Explanations

    keywords related to operations and processes in programming and engineering contexts

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

    Follows "operation" or related terms

    np_acts-logits-general · gemini-2.0-flash

    operation or operating

    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
    ագրություններ
    -0.72
    AndEndTag
    -0.58
     تضيفلها
    -0.52
    enumi
    -0.51
    MemoryWarning
    -0.49
    onoi
    -0.49
    Slf
    -0.46
    bsen
    -0.45
    IANGLES
    -0.44
    rungsseite
    -0.43
    POSITIVE LOGITS
     operation
    3.56
     Operation
    3.24
    operation
    3.15
    Operation
    3.06
     OPERATION
    2.96
     oper
    2.81
     operate
    2.76
     operations
    2.74
     OPER
    2.70
    OPERATION
    2.68
    Activations Density 0.224%

    No Known Activations