© 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. 869
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or qualifications involving "and" or "but"

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

    preceding relative pronouns (which, that, who)

    np_acts-logits-general · gemini-2.0-flash

    relative clauses

    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
     kasarigan
    -0.67
    lapsingToolbar
    -0.56
     %}
    -0.55
    Extinguishing
    -0.54
    ąc
    -0.54
    warted
    -0.52
    ))))))))
    -0.51
    SharedDtor
    -0.51
    qtype
    -0.50
    felder
    -0.49
    POSITIVE LOGITS
     which
    2.28
     whose
    2.11
    whose
    1.86
    which
    1.81
     who
    1.78
     cuya
    1.60
     cuyo
    1.58
     cuyas
    1.58
     WHICH
    1.57
     Whose
    1.57
    Activations Density 0.323%

    No Known Activations