Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14454
    Prev
    Next
    INDEX
    Explanations

    expressions of love and affection towards individuals and relationships

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

    Followed by words indicating deep affection

    np_acts-logits-general · gemini-2.0-flash

    intense love for someone

    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
    transQ
    -0.90
    ंदीखरीदारी
    -0.88
     متعلقه
    -0.85
    ########.
    -0.84
    
    -0.78
    ListItemIcon
    -0.75
    //
    -0.75
    ">//
    -0.71
    EndGlobalSection
    -0.69
    évaluateur
    -0.69
    POSITIVE LOGITS
     dearly
    0.76
     profondément
    0.60
     passionately
    0.59
     profundamente
    0.54
     unconditionally
    0.53
     deeply
    0.53
     altrett
    0.49
     intensely
    0.48
     wholeheartedly
    0.48
     madly
    0.48
    Activations Density 0.186%

    No Known Activations