© 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. 14974
    Prev
    Next
    INDEX
    Explanations

    significant numerical values or dates in the 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
    <bos>
    -0.96
     autorytatywna
    -0.68
     تضيفلها
    -0.66
    ValueStyle
    -0.62
    tagHelperRunner
    -0.57
    licópter
    -0.55
     Koss
    -0.54
    DidLoad
    -0.54
    Ausbildung
    -0.54
    icose
    -0.53
    POSITIVE LOGITS
    __':
    
    0.76
    MessageOf
    0.66
    __":
    
    0.65
    談社
    0.63
    ябрь
    0.62
     åren
    0.59
    fromnode
    0.58
     milliers
    0.58
     quæ
    0.57
     années
    0.56
    Activations Density 0.110%

    No Known Activations