© 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. 2883
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or contact information

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

    Numbers, especially after prefixes or codes

    np_acts-logits-general · gemini-2.0-flash

    phone numbers and codes

    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
     dietro
    -0.54
     franca
    -0.54
     detrás
    -0.54
    kloped
    -0.53
    twimg
    -0.51
     behind
    -0.51
     عم
    -0.49
    клопе
    -0.49
    hounds
    -0.47
    ╗
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.83
     IBOutlet
    0.67
     avoient
    0.61
    :✨
    0.60
     RIPRODUZIONE
    0.60
    Tembelea
    0.60
     OMITBAD
    0.59
     définiti
    0.59
    ніципа
    0.58
     theſe
    0.58
    Activations Density 0.034%

    No Known Activations