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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 15780
    Prev
    Next
    INDEX
    Explanations

    patterns related to array and matrix operations within programming syntax

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

    Coordinates or positions (e.g., 0, 0)

    np_acts-logits-general · gemini-2.0-flash

    coordinates surrounded by commas or semicolons

    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
     ?>>
    -0.51
    EREF
    -0.45
    etas
    -0.43
    seitig
    -0.43
    ong
    -0.42
     %@",
    -0.42
     khúc
    -0.42
    ложения
    -0.41
    %@",
    -0.41
     St
    -0.40
    POSITIVE LOGITS
     Roskov
    1.44
     CreateTagHelper
    1.06
     للاسماء
    1.01
    InjectAttribute
    0.99
    ftagPool
    0.95
    StoryboardSegue
    0.89
     DialogInterface
    0.84
    makeConstraints
    0.82
     виправивши
    0.82
    AddHtmlAttribute
    0.76
    Activations Density 0.596%

    No Known Activations