© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9748
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and their representation

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

    Code elements: array, object, promise

    np_acts-logits-general · gemini-2.0-flash

    programming data structures and promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obald
    -0.79
     متعلقه
    -0.72
    VersionUID
    -0.71
    FunctionFlags
    -0.70
    !*\
    -0.66
    AddTagHelper
    -0.65
     myſelf
    -0.63
    printStackTrace
    -0.61
    🏾
    -0.61
    ineno
    -0.60
    POSITIVE LOGITS
     containing
    0.64
     representing
    0.59
    ArrowToggle
    0.59
    形式
    0.53
     whose
    0.51
     representation
    0.49
    类型的
    0.48
     linkovi
    0.47
     WebApplication
    0.45
     or
    0.44
    Activations Density 0.800%

    No Known Activations