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. 4-GEMMASCOPE-RES-16K
    6. 1248
    Prev
    Next
    INDEX
    Explanations

    code snippets and formatting characters used in programming documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.67
    </em>
    -0.63
     Bar
    -0.58
    GoogleMap
    -0.58
     waters
    -0.57
    —
    -0.55
     her
    -0.51
     Hume
    -0.51
    gänger
    -0.51
     O
    -0.49
    POSITIVE LOGITS
    ```
    3.62
     ```
    2.46
    ```
    
    1.75
    +```
    1.72
    ````
    1.31
    -```
    1.31
     purpoſe
    1.06
    ſelves
    0.99
     Diſ
    0.97
    "`
    0.96
    Activations Density 0.220%

    No Known Activations