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. 11-GEMMASCOPE-RES-16K
    6. 7195
    Prev
    Next
    INDEX
    Explanations

    references to specific names and terms related to individuals or entities in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActivityCompat
    -0.92
    InjectMocks
    -0.92
    mybatisplus
    -0.90
    swick
    -0.89
    skraft
    -0.89
    shmi
    -0.87
    çalves
    -0.86
     propOrder
    -0.85
    begingroup
    -0.84
    ikyuu
    -0.84
    POSITIVE LOGITS
    er
    2.32
    ER
    1.67
    ler
    1.25
    der
    1.21
    ter
    1.19
    ner
    1.17
    ber
    1.14
    rer
    1.13
    mer
    1.09
    ier
    1.08
    Activations Density 0.813%

    No Known Activations