© 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. 9652
    Prev
    Next
    INDEX
    Explanations

    relationships and familial connections between individuals

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

    Family relationships (aunts, uncles, cousins, nephews, nieces)

    np_acts-logits-general · gemini-2.0-flash

    family member relationships

    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
    =$?
    -0.70
    NotEqualTo
    -0.61
    </thead>
    -0.60
     المعيارى
    -0.59
     TextAppearance
    -0.56
    mich
    -0.56
    كونات
    -0.55
     ressource
    -0.55
     Voc
    -0.54
     Iba
    -0.54
    POSITIVE LOGITS
     cousins
    1.40
     cousin
    1.33
     nephews
    1.26
     nephew
    1.24
     nieces
    1.22
     uncle
    1.19
     uncles
    1.14
     aunt
    1.12
     niece
    1.10
     aunts
    1.05
    Activations Density 0.176%

    No Known Activations