© 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. 5-GEMMASCOPE-RES-16K
    6. 15122
    Prev
    Next
    INDEX
    Explanations

    programming and assembly-related terms and references

    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
    migrationBuilder
    -0.70
     للمعارف
    -0.62
    <bos>
    -0.59
    Bibliograf
    -0.59
    mybatisplus
    -0.57
    Искәрмәләр
    -0.56
    CrossRef
    -0.53
    Erreferentziak
    -0.51
    offsetof
    -0.49
     Référence
    -0.49
    POSITIVE LOGITS
    DoubleQuotes
    1.66
    ("")]
    1.38
    Clik
    1.12
    __":
    1.07
    ("")]
    
    1.05
     noqa
    1.01
    ChildScrollView
    1.00
    __':
    0.94
     createState
    0.91
     actionPerformed
    0.87
    Activations Density 0.032%

    No Known Activations