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. 25-GEMMASCOPE-RES-16K
    6. 8336
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric values and their organization

    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
     Shakspeare
    -0.62
     purpoſe
    -0.59
     ſtate
    -0.58
     Monfieur
    -0.57
     ſeveral
    -0.56
     Efq
    -0.55
     pleaſure
    -0.53
     twelve
    -0.52
     nine
    -0.52
    Espèce
    -0.51
    POSITIVE LOGITS
    6
    0.66
    8
    0.64
    5
    0.64
    7
    0.63
    脚注の使い方
    0.62
    4
    0.61
    Према
    0.61
    3
    0.60
    9
    0.59
    ربای
    0.58
    Activations Density 0.281%

    No Known Activations