© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9294
    Prev
    Next
    INDEX
    Explanations

    references to prominent criminal cases or events

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

    Git diff index numbers

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.95
    RegressionTest
    -0.94
     дописавши
    -0.89
     defaultstate
    -0.86
    XmlAccessorType
    -0.85
    WriteTagHelper
    -0.84
     חיצוניים
    -0.83
    #+#
    -0.81
    PyExc
    -0.79
    DoubleQuotes
    -0.79
    POSITIVE LOGITS
    4
    0.56
    1
    0.53
    8
    0.52
    5
    0.51
    6
    0.50
    9
    0.50
    2
    0.49
    0
    0.48
    7
    0.48
    3
    0.47
    Activations Density 0.603%

    No Known Activations