© 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. 11510
    Prev
    Next
    INDEX
    Explanations

    elements related to procedural guidelines and recommendations

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

    Requirements or conditions

    np_acts-logits-general · gemini-2.0-flash

    involve these words

    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
     Diſ
    -0.59
    WriteTagHelper
    -0.59
     ſind
    -0.56
    awtextra
    -0.56
    ]='\
    -0.55
     pleaſure
    -0.54
     Majefty
    -0.53
    neſs
    -0.53
     leaſt
    -0.53
     pinulongan
    -0.52
    POSITIVE LOGITS
     involve
    1.01
     involves
    0.81
     consist
    0.80
     include
    0.74
     coincide
    0.71
     contain
    0.69
     entail
    0.68
     reflect
    0.68
     resemble
    0.66
     consisted
    0.66
    Activations Density 2.306%

    No Known Activations