© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12383
    Prev
    Next
    INDEX
    Explanations

    components and libraries related to IntelliJ and its OpenAPI, along with specific programming constructs in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.02
     ProtoMessage
    -0.91
     consultato
    -0.91
    لينكات
    -0.89
     للاسماء
    -0.85
     propOrder
    -0.71
    Datuak
    -0.69
    原始内容存档于
    -0.62
    yntaxException
    -0.61
    GOTREF
    -0.59
    POSITIVE LOGITS
    mybatisplus
    2.16
    rxjs
    1.27
    matchCondition
    1.17
    bukkit
    0.95
    multirow
    0.94
    nestjs
    0.83
    intellij
    0.81
    apimachinery
    0.78
    NgModule
    0.76
    +:+
    0.75
    Activations Density 0.015%

    No Known Activations