© 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. 18-GEMMASCOPE-RES-16K
    6. 14587
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or numerical information

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

    The number "0" followed by another number

    np_acts-logits-general · gemini-2.0-flash

    years and numbers

    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
    ViewFeatures
    -0.84
    GEBURTSDATUM
    -0.82
    Datuak
    -0.70
    RuleContext
    -0.68
     CanadaChoose
    -0.68
    ✨:
    -0.63
     '\\;'
    -0.62
     typelib
    -0.62
     NSCoder
    -0.62
    ])):
    -0.61
    POSITIVE LOGITS
    0
    1.11
    AndEndTag
    0.79
    1
    0.63
     fhould
    0.60
     FormGroup
    0.53
     fhort
    0.52
     aught
    0.49
    шой
    0.49
     atteinte
    0.49
     Suz
    0.48
    Activations Density 0.175%

    No Known Activations