© 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. 28235
    Prev
    Next
    INDEX
    Explanations

    phrases related to various states of being and their implications

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

    lack and insufficiency

    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
     AttributeSet
    -0.59
     ExecuteAsync
    -0.58
    testens
    -0.57
    VALID
    -0.54
    iteracy
    -0.53
     σω
    -0.52
    ண்டும்
    -0.51
    ListItemIcon
    -0.50
    richTextPanel
    -0.50
    assertNotNull
    -0.50
    POSITIVE LOGITS
     insufficient
    0.81
     inadequate
    0.69
     inadequ
    0.68
     inferior
    0.67
     unreliable
    0.65
     underwhelming
    0.65
     inefficient
    0.63
     insufic
    0.62
     NSCoder
    0.62
     lacked
    0.61
    Activations Density 0.507%

    No Known Activations