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. 5-GEMMASCOPE-RES-16K
    6. 3561
    Prev
    Next
    INDEX
    Explanations

    references to the Hibernate framework and its components in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnInit
    -0.76
    SpringBootTest
    -0.60
    ValueStyle
    -0.58
    Grady
    -0.58
    appcompat
    -0.55
    zeich
    -0.55
    cshtml
    -0.53
    ujud
    -0.53
    ExtendWith
    -0.51
    duma
    -0.51
    POSITIVE LOGITS
    TagMode
    2.19
    ScopeManager
    1.82
    SequentialGroup
    1.65
    BuildContext
    1.22
    mybatisplus
    1.16
    SourceChecksum
    1.07
    ruptedException
    0.99
    InjectAttribute
    0.97
    BeginContext
    0.96
    WEBPACK
    0.90
    Activations Density 0.005%

    No Known Activations