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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 8703
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving ranges and limits

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

    Mathematical or programming variables

    np_acts-logits-general · gemini-2.0-flash

    interval endpoints or limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    },[
    -0.55
     PyTuple
    -0.52
    Chham
    -0.51
    */].
    -0.50
    ]]:
    -0.50
     utafitiHapana
    -0.49
    strerror
    -0.49
    })$}
    -0.49
     after
    -0.48
    InitVars
    -0.48
    POSITIVE LOGITS
     ועד
    0.85
     hingga
    0.78
     până
    0.77
     kuni
    0.76
     jusqu
    0.76
    GEBURTS
    0.75
     Jusqu
    0.75
     लेकर
    0.74
    到
    0.74
     hanggang
    0.73
    Activations Density 0.717%

    No Known Activations