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. 23-GEMMASCOPE-RES-16K
    6. 11160
    Prev
    Next
    INDEX
    Explanations

    components related to adhesive properties and their applications in various materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italij
    -0.71
    MemoryWarning
    -0.70
     springfox
    -0.69
    KURZBESCHREIBUNG
    -0.66
     ब्रेकडाउन
    -0.61
    ंदीखरीदारी
    -0.60
     GenerationType
    -0.59
     noqa
    -0.58
    tagHelperRunner
    -0.58
     NUKAT
    -0.57
    POSITIVE LOGITS
     adhesive
    1.53
     Adhesive
    1.34
     stick
    1.28
     sticky
    1.26
    adhesive
    1.21
     adhesives
    1.21
     sticking
    1.20
     STICK
    1.19
    Stick
    1.18
     Stick
    1.16
    Activations Density 0.410%

    No Known Activations