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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 14623
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the current time or moment, often using the word "now" or similar expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.60
    期刊论文
    -0.56
     مشين
    -0.53
    الإنجليزية
    -0.50
    Portale
    -0.49
     AttributeSet
    -0.49
    Brought
    -0.46
    ReusableCell
    -0.46
    линд
    -0.44
    一言
    -0.44
    POSITIVE LOGITS
     currently
    1.56
    currently
    1.47
     presently
    1.40
     Currently
    1.33
    Currently
    1.31
     current
    1.20
     momentan
    1.20
     CURRENT
    1.19
     Presently
    1.14
    CURRENT
    1.12
    Activations Density 0.125%

    No Known Activations