© 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. 8385
    Prev
    Next
    INDEX
    Explanations

    terms and keywords related to product tags and their management in a system

    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
    +#+#
    -0.59
    TypedDataSet
    -0.53
    rxjs
    -0.52
     تانيه
    -0.52
    SequentialGroup
    -0.51
    EDEFAULT
    -0.50
     GenerationType
    -0.49
    abetes
    -0.49
    lück
    -0.49
    toThrow
    -0.48
    POSITIVE LOGITS
     tag
    3.85
     Tag
    3.60
     tags
    3.45
    Tag
    3.44
    tag
    3.38
     tagging
    3.10
     Tags
    3.09
    tags
    2.85
     TAG
    2.85
    Tags
    2.77
    Activations Density 0.265%

    No Known Activations