© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7103
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to support and assistance in various contexts

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

    "support"

    np_acts-logits-general · gemini-2.0-flash

    support for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HostException
    -0.74
    ValueStyle
    -0.64
    IndentedString
    -0.64
     consultato
    -0.61
    HandlerContext
    -0.60
    Autoritní
    -0.60
    httphttps
    -0.59
    alga
    -0.59
     digitais
    -0.58
    "\
    -0.58
    POSITIVE LOGITS
     Supports
    0.72
     supports
    0.69
    Supports
    0.69
    /*
    0.66
    fully
    0.63
    supports
    0.58
    IVE
    0.58
     support
    0.53
     structure
    0.53
     penuh
    0.53
    Activations Density 0.178%

    No Known Activations