© 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. 3986
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest a conversation, agreement, or interaction between individuals

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

    preceding conjunctions "and" or "but"

    np_acts-logits-general · gemini-2.0-flash

    conjunctions or 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
    omitempty
    -0.55
     unknownFields
    -0.49
    hObject
    -0.47
    tagHelperRunner
    -0.42
    ]")]
    -0.41
    dited
    -0.40
    janje
    -0.40
    atschappij
    -0.39
    fieldLabel
    -0.39
    thentication
    -0.38
    POSITIVE LOGITS
     Darauf
    0.88
    setVerticalGroup
    0.73
    rungsseite
    0.68
    被他
    0.67
    PhysRevD
    0.65
     réessayer
    0.65
    <?
    0.62
     bezeichneter
    0.62
    ConstraintMaker
    0.61
     whereupon
    0.60
    Activations Density 0.278%

    No Known Activations