© 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. 8381
    Prev
    Next
    INDEX
    Explanations

    references to "hot" as well as descriptions of summer or heat-related topics

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

    Following "hot"

    np_acts-logits-general · gemini-2.0-flash

    hot followed by specific nouns

    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
    Bronnen
    -0.69
    évaluateur
    -0.65
    ArgsConstructor
    -0.55
    DatabaseError
    -0.54
    AYSIA
    -0.54
    edos
    -0.54
    }))
    
    -0.53
     understatement
    -0.52
     UserManager
    -0.51
     Caballero
    -0.51
    POSITIVE LOGITS
    dog
    0.70
     tub
    0.65
    dogs
    0.63
    rod
    0.61
     rod
    0.59
     dog
    0.57
    rods
    0.55
    chk
    0.55
    CppMethod
    0.55
     dogs
    0.55
    Activations Density 0.073%

    No Known Activations