© 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. 5-GEMMASCOPE-RES-16K
    6. 14692
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements in text

    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
     تانيه
    -0.74
     препратки
    -0.70
    ỡng
    -0.68
     säll
    -0.66
     varandra
    -0.65
     Проци
    -0.65
    liflower
    -0.65
     vastaan
    -0.64
    mybatisplus
    -0.64
     dezelve
    -0.64
    POSITIVE LOGITS
    xn
    0.53
    ReferenceEquals
    0.53
    derive
    0.50
    帖最后由
    0.50
    PACK
    0.48
     IndexPath
    0.48
    ❋
    0.48
    DataSnapshot
    0.47
    gallon
    0.46
    IBAction
    0.45
    Activations Density 0.254%

    No Known Activations