© 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. 24-GEMMASCOPE-RES-16K
    6. 12586
    Prev
    Next
    INDEX
    Explanations

    references to entities and their relationships

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

    "entity" or entities"

    np_acts-logits-general · gemini-2.0-flash

    entity

    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
    ंदीखरीदारी
    -0.66
     tube
    -0.61
     tubes
    -0.61
     protoimpl
    -0.58
    tube
    -0.58
     ComVisible
    -0.58
    httphttps
    -0.58
     TUBE
    -0.56
    PYX
    -0.56
     Tube
    -0.55
    POSITIVE LOGITS
     entity
    3.08
    entity
    2.83
     Entity
    2.74
    Entity
    2.57
     entities
    2.27
     ENTITY
    2.26
    ENTITY
    2.19
     Entities
    2.02
    getEntity
    1.89
    entities
    1.82
    Activations Density 0.088%

    No Known Activations