© 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. 25-GEMMASCOPE-RES-16K
    6. 10592
    Prev
    Next
    INDEX
    Explanations

    features related to product specifications and standards

    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
     CreateTagHelper
    -0.86
    ьаж
    -0.58
    Vidite
    -0.54
     AsyncTask
    -0.54
    égard
    -0.51
    élène
    -0.51
    ärna
    -0.51
    titleMargin
    -0.50
     يتيمه
    -0.50
    ListItemIcon
    -0.49
    POSITIVE LOGITS
     allowing
    2.08
     enabling
    1.89
     making
    1.86
     giving
    1.78
    allowing
    1.74
     ensuring
    1.71
     thereby
    1.59
     helping
    1.57
     Allowing
    1.57
     permitiendo
    1.52
    Activations Density 1.600%

    No Known Activations