© 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. 24-GEMMASCOPE-RES-16K
    11. 15988
    Prev
    Next
    INDEX
    Explanations

    connections between spirituality and mental health

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

    about family or close connections

    np_acts-logits-general · gemini-2.0-flash

    relationship, relations, tie, collaboration, communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.74
    anguardia
    -0.59
     MediatR
    -0.55
    ItemBackground
    -0.52
    écnicas
    -0.52
     AudioClip
    -0.52
    MultipartFile
    -0.51
    ziek
    -0.48
     Normdatei
    -0.48
     demografica
    -0.47
    POSITIVE LOGITS
     relationship
    3.07
     relationships
    2.76
     relations
    2.63
    relationship
    2.55
     relation
    2.49
     Relationship
    2.43
     RELATIONSHIP
    2.40
    Relationship
    2.36
     Relationships
    2.23
     RELATION
    2.20
    Activations Density 0.762%

    No Known Activations