© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1856
    Prev
    Next
    INDEX
    Explanations

    citations and references in academic writing

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

    References/citations after names

    np_acts-logits-general · gemini-2.0-flash

    citations with @ and names

    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
    …
    -0.65
    assertRaises
    -0.56
    ….
    -0.53
    …..
    -0.52
    ================
    -0.51
    flink
    -0.49
    EnableWeb
    -0.48
    ...
    -0.47
    ……
    -0.47
    ....
    -0.47
    POSITIVE LOGITS
     متعلقه
    0.72
    tagHelperRunner
    0.72
     >=",
    0.69
    TagMode
    0.68
    })));
    0.67
     INSEE
    0.66
     AssemblyProduct
    0.65
     Италијани
    0.65
    quels
    0.63
     nahilalakip
    0.62
    Activations Density 0.501%

    No Known Activations