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. 15-GEMMASCOPE-RES-16K
    6. 12751
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to systems and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.62
    twimg
    -0.60
    readAs
    -0.53
     nhận
    -0.51
     recens
    -0.49
    OGND
    -0.47
     browning
    -0.46
    executeUpdate
    -0.45
    CompoundButton
    -0.45
    évaluateur
    -0.45
    POSITIVE LOGITS
    StoryboardSegue
    1.16
    StackNavigator
    0.84
    routeProvider
    0.83
    SceneManagement
    0.81
    stateProvider
    0.81
     RouterModule
    0.81
     useRouter
    0.79
    withIdentifier
    0.75
    PageRoute
    0.75
    FXMLLoader
    0.74
    Activations Density 0.190%

    No Known Activations