© 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. 842
    Prev
    Next
    INDEX
    Explanations

    various types of method declarations and related structural elements in code

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

    Code snippets with "get" method calls

    np_acts-logits-general · gemini-2.0-flash

    get and set methods

    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
    mesin
    -0.44
     I
    -0.43
     daran
    -0.43
     And
    -0.42
     råd
    -0.42
    ಾದ
    -0.41
    <i>
    -0.41
    <em>
    -0.40
     du
    -0.40
     ans
    -0.40
    POSITIVE LOGITS
     ujednoznacz
    0.98
     Paglinawan
    0.96
     get
    0.94
    новништво
    0.90
    enumii
    0.87
    WithIOException
    0.85
     الرياضيه
    0.84
    BufferException
    0.83
    ViewFeatures
    0.83
    RegistryLite
    0.83
    Activations Density 0.123%

    No Known Activations