Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 10864
    Prev
    Next
    INDEX
    Explanations

    elements related to commitment and action towards achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pued
    -0.49
     Функ
    -0.44
     gag
    -0.42
    opathology
    -0.42
    ễn
    -0.42
    ECO
    -0.42
    Функ
    -0.42
     sorti
    -0.41
     poveznice
    -0.41
     Sollte
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    1.03
    AndEndTag
    0.90
    InputTagHelper
    0.82
    InvalidProtocol
    0.71
    ManagedBean
    0.66
    ItemLayout
    0.65
    GraphicsUnit
    0.62
     дописавши
    0.62
    ISupport
    0.61
    PyExc
    0.60
    Activations Density 0.171%

    No Known Activations