© 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. 4-GEMMASCOPE-RES-16K
    6. 9866
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions associated with appreciation or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.64
    dify
    -0.59
    ReusableCell
    -0.59
     IAP
    -0.54
    antz
    -0.53
     continúas
    -0.52
     SVD
    -0.51
     Hän
    -0.50
    Tentang
    -0.50
    Especial
    -0.49
    POSITIVE LOGITS
     téléchargez
    0.62
    μισ
    0.59
    følgelig
    0.57
    Бахар
    0.56
    BeginContext
    0.56
     devrez
    0.54
    abah
    0.54
    ыгана
    0.54
     crossorigin
    0.54
    "]/
    0.53
    Activations Density 0.861%

    No Known Activations