Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5792
    Prev
    Next
    INDEX
    Explanations

    phrases related to software updates and feature availability

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

    preceding "support" or "supports"

    np_acts-logits-general · gemini-2.0-flash

    announced support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.76
    ंदीखरीदारी
    -0.68
    textTheme
    -0.59
     Inflate
    -0.54
    abetes
    -0.53
    MockMvc
    -0.51
    HandlerContext
    -0.50
    abestanden
    -0.50
    ändigt
    -0.49
    writeFieldEnd
    -0.49
    POSITIVE LOGITS
     support
    4.27
    support
    3.89
     Support
    3.87
    Support
    3.79
     SUPPORT
    3.56
     supports
    3.38
    SUPPORT
    3.37
     supporting
    3.30
     supported
    3.16
    upport
    3.04
    Activations Density 0.761%

    No Known Activations