© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    instructions or recommendations to prevent undesirable outcomes

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

    "Avoid" and subsequent actions/objects

    np_acts-logits-general · gemini-2.0-flash

    avoiding specific problems

    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
     فريبيس
    -0.66
     ferdig
    -0.65
     vertes
    -0.62
    Datuak
    -0.62
     publiques
    -0.59
     extérieures
    -0.58
    orithmic
    -0.57
     fær
    -0.56
     dieux
    -0.55
     réguli
    -0.55
    POSITIVE LOGITS
     Avoid
    0.75
    noinspection
    0.74
    Avoid
    0.73
     unnecessary
    0.72
     AVOID
    0.71
     avoid
    0.69
     avoiding
    0.68
     pitfalls
    0.68
    avoid
    0.68
     defaultstate
    0.66
    Activations Density 0.124%

    No Known Activations