© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28343
    Prev
    Next
    INDEX
    Explanations

    the beginning of sections or paragraphs in documents

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

    Q: followed by specific terms

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AutoField
    -0.60
    writeFieldEnd
    -0.51
    shaft
    -0.48
    BASEPATH
    -0.46
     defaultstate
    -0.45
    \{\\
    -0.45
    designed
    -0.43
    힣
    -0.43
    出版年
    -0.43
     Normdatei
    -0.43
    POSITIVE LOGITS
     SwitchCompat
    0.71
    EDEFAULT
    0.69
    SerializedSize
    0.66
    SequentialGroup
    0.66
    Попис
    0.56
    ̈́
    0.56
    LoginComponent
    0.55
    &$
    0.54
    ungkinan
    0.54
     AppCompatTheme
    0.52
    Activations Density 0.010%

    No Known Activations