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. 18-GEMMASCOPE-RES-16K
    6. 15114
    Prev
    Next
    INDEX
    Explanations

    elements that indicate personal characteristics and social interactions

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

    Follows punctuation or special characters (~, -, :, ], \)

    np_acts-logits-general · gemini-2.0-flash

    symbols followed by introductory words

    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
     المعيارى
    -0.64
    eux
    -0.61
    NonQuery
    -0.60
    éric
    -0.59
     Optics
    -0.58
     estekak
    -0.58
    OGND
    -0.58
    PyExc
    -0.57
     AspNetCore
    -0.57
    ()][
    -0.56
    POSITIVE LOGITS
     This
    1.12
     The
    1.11
    The
    1.03
    This
    0.99
     There
    0.92
     When
    0.87
     Although
    0.86
    There
    0.84
     Because
    0.82
    When
    0.79
    Activations Density 0.352%

    No Known Activations