© 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. 2449
    Prev
    Next
    INDEX
    Explanations

    comparative terms indicating a reduction or lesser quality

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

    "less" followed by comparative words

    np_acts-logits-general · gemini-2.0-flash

    less than

    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
     BoxDecoration
    -0.75
     doInBackground
    -0.60
    données
    -0.60
     onCreateView
    -0.59
    ()]
    
    -0.58
    unpublished
    -0.56
     hinweg
    -0.55
    Personensuche
    -0.55
    IndentedString
    -0.54
     uncut
    -0.54
    POSITIVE LOGITS
     than
    0.95
    than
    0.83
    ens
    0.82
     THAN
    0.81
    ening
    0.69
     likely
    0.69
     fortunate
    0.67
     (<
    0.66
    ors
    0.65
     Than
    0.65
    Activations Density 0.113%

    No Known Activations