© 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. 10-GEMMASCOPE-RES-16K
    6. 1823
    Prev
    Next
    INDEX
    Explanations

    phrases and sentiments related to understanding and forgiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.70
    __":
    
    -0.70
    FontStyle
    -0.69
    Literals
    -0.66
    RTCK
    -0.65
    bewerken
    -0.64
    bono
    -0.64
     calendriers
    -0.63
    ++]=
    -0.61
    chiere
    -0.61
    POSITIVE LOGITS
    Kjelder
    0.51
     cauza
    0.51
     understandable
    0.49
    难怪
    0.48
    desen
    0.48
    DataAnnotations
    0.47
     why
    0.47
    >{@
    0.47
     verständ
    0.45
     reasons
    0.45
    Activations Density 0.279%

    No Known Activations