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. 5-GEMMASCOPE-RES-16K
    6. 13106
    Prev
    Next
    INDEX
    Explanations

    imports and references to the Spring Framework and similar libraries

    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
    BeginContext
    -0.97
    AutoScaleMode
    -0.72
    ParallelGroup
    -0.70
    ScopeManager
    -0.69
    httphttps
    -0.65
    دانشنامهٔ
    -0.64
     BoxFit
    -0.62
    setVerticalGroup
    -0.62
    LayoutStyle
    -0.61
    addCriterion
    -0.60
    POSITIVE LOGITS
    DebuggerNonUser
    1.22
    springframework
    0.98
    gdx
    0.96
    AndEndTag
    0.84
    цездатний
    0.81
    ErrUnexpectedEOF
    0.69
    esModule
    0.69
     noqa
    0.67
    MigrationBuilder
    0.66
     ddelweddau
    0.64
    Activations Density 0.025%

    No Known Activations