© 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. 25-GEMMASCOPE-RES-16K
    11. 1078
    Prev
    Next
    INDEX
    Explanations

    quantitative indicators of frequency and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autrement
    -0.73
     referenties
    -0.71
     BufferedReader
    -0.61
     cauza
    -0.59
    aarrggbb
    -0.59
     démission
    -0.59
    berdayakan
    -0.59
     utafitiHapana
    -0.58
     inoxydable
    -0.56
     the
    -0.56
    POSITIVE LOGITS
     round
    0.94
     batch
    0.90
     iteration
    0.88
     installment
    0.84
     few
    0.76
     instalment
    0.74
     incarnation
    0.73
     wave
    0.73
     phase
    0.72
     chapter
    0.71
    Activations Density 0.348%

    No Known Activations