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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7148
    Prev
    Next
    INDEX
    Explanations

    specific numerical and statistical references

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

    Follows a question or a colon

    np_acts-logits-general · gemini-2.0-flash

    question/answer pairs

    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
    tvguidetime
    -1.21
    rungsseite
    -0.86
     تضيفلها
    -0.85
    ajin
    -0.81
    brainly
    -0.80
    hyrchwyd
    -0.80
     BoxDecoration
    -0.79
    Cyfeiriadau
    -0.78
     =",
    -0.77
     nahilalakip
    -0.77
    POSITIVE LOGITS
    The
    1.31
     The
    1.11
    There
    0.95
    It
    0.91
    This
    0.91
    If
    0.87
    Also
    0.84
    When
    0.84
    I
    0.84
     There
    0.84
    Activations Density 0.243%

    No Known Activations