© 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. 1-GEMMASCOPE-RES-16K
    6. 3906
    Prev
    Next
    INDEX
    Explanations

    instances of the term "offset" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.68
     autorytatywna
    -0.65
    TableAdapter
    -0.62
    RegistryLite
    -0.62
     exercising
    -0.59
     QtGui
    -0.59
     corpi
    -0.58
    ModelAdmin
    -0.58
     للمعارف
    -0.57
    xae
    -0.57
    POSITIVE LOGITS
     offset
    1.10
     Offset
    0.92
    Offset
    0.92
    offset
    0.87
     peak
    0.81
    Portail
    0.77
     peaks
    0.77
     offsets
    0.76
     edges
    0.70
     Peaks
    0.67
    Activations Density 0.132%

    No Known Activations