© 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-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15467
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quantity or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    -0.49
    IntoConstraints
    -0.49
    Datuak
    -0.46
    eningrad
    -0.46
    WebElementEntity
    -0.44
    adaptiveStyles
    -0.42
     ascend
    -0.42
    UserScript
    -0.42
     Roskov
    -0.41
    הערות
    -0.40
    POSITIVE LOGITS
     lot
    0.74
     LOT
    0.64
     Lot
    0.64
    Beaucoup
    0.61
     much
    0.60
     paljon
    0.60
     MUCH
    0.59
    Mucho
    0.59
     lotta
    0.58
     vieles
    0.58
    Activations Density 0.123%

    No Known Activations