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. 12352
    Prev
    Next
    INDEX
    Explanations

    content related to warnings and disclaimers about sensitive or graphic material

    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
    ValueMap
    -0.51
     satisfait
    -0.49
    BASEPATH
    -0.48
     Protobuf
    -0.47
    größern
    -0.47
     physiques
    -0.47
     trực
    -0.47
    arikat
    -0.46
     ويكيپيديا
    -0.46
    ISSN
    -0.46
    POSITIVE LOGITS
     fanfic
    1.06
     fanfiction
    1.05
     fic
    1.02
     AU
    0.91
    fanfic
    0.90
     Fic
    0.82
     smut
    0.81
     pairings
    0.81
    Fandom
    0.80
     fandom
    0.79
    Activations Density 0.281%

    No Known Activations