© 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. 16164
    Prev
    Next
    INDEX
    Explanations

    statistical data and trends related to veterinary conditions

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

    Code or bracketed information

    np_acts-logits-general · gemini-2.0-flash

    references and identifiers

    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
    ?",
    -0.80
     CreateTagHelper
    -0.79
     EconPapers
    -0.79
    <eos>
    -0.75
     ?"
    -0.74
    !"
    -0.74
    writeFieldEnd
    -0.72
    ://"
    -0.70
    !",
    -0.70
    Билгалдахарш
    -0.69
    POSITIVE LOGITS
    \_
    1.09
    _
    1.06
    }
    0.93
    .}
    0.91
    }\\
    0.90
    }{
    0.89
    }_
    0.84
    }\
    0.81
    }
    
    0.79
    ._
    0.76
    Activations Density 0.597%

    No Known Activations