© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6866
    Prev
    Next
    INDEX
    Explanations

    references to statistical methods and their contributors, particularly in the context of research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Citations containing years

    np_acts-logits-general · gemini-2.0-flash

    academic findings citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.71
    RectangleBorder
    -0.64
    XmlAccessorType
    -0.59
    Autoritní
    -0.59
    BagConstraints
    -0.58
     FetchType
    -0.57
     ProtoMessage
    -0.56
    րի
    -0.54
    |}{$
    -0.54
    ]='\
    -0.53
    POSITIVE LOGITS
     originaux
    0.67
     fört
    0.62
    rungsseite
    0.60
     laaj
    0.57
    excellents
    0.56
     indépend
    0.54
     détaillés
    0.52
     franceses
    0.51
     récents
    0.51
     Ellos
    0.51
    Activations Density 1.639%

    No Known Activations