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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2341
    Prev
    Next
    INDEX
    Explanations

    emotional language related to personal experiences and challenges

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

    Adjectives describing an abstract concept

    np_acts-logits-general · gemini-2.0-flash

    qualities of abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auffi
    -0.77
    UnknownFields
    -0.76
    EndGlobalSection
    -0.76
     ainfi
    -0.71
    "]);
    
    -0.68
     ſtate
    -0.66
     ]
    
    -0.65
     мәкал
    -0.64
     iſt
    -0.63
     ſta
    -0.63
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.68
    SequentialGroup
    0.60
     vibe
    0.60
     mindset
    0.58
     mentality
    0.57
     circonstances
    0.55
     avenue
    0.52
     morales
    0.51
     equation
    0.50
     froide
    0.50
    Activations Density 0.418%

    No Known Activations