© 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. 4270
    Prev
    Next
    INDEX
    Explanations

    conversational cues and questions about relationships and emotions

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

    Text followed by conjunctions like "but", "if", "so"

    np_acts-logits-general · gemini-2.0-flash

    the way it is

    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
     &&
    -0.72
     arvio
    -0.62
     mihi
    -0.60
    ">—
    -0.59
     ―――――
    -0.58
     elbise
    -0.58
    }>
    -0.58
     [
    -0.56
    прочем
    -0.56
       
    -0.55
    POSITIVE LOGITS
     Its
    1.51
     its
    1.48
    Its
    1.44
     theres
    1.32
     thats
    1.21
     i
    1.20
     shes
    1.14
    its
    1.11
     Thats
    1.08
     dont
    1.05
    Activations Density 0.534%

    No Known Activations