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. 15-GEMMASCOPE-RES-16K
    6. 12580
    Prev
    Next
    INDEX
    Explanations

    noun phrases related to entity names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]));
    
    -0.72
    hobo
    -0.67
    }));
    
    -0.64
    sol
    -0.63
     trist
    -0.62
    ```
    
    -0.60
     kuid
    -0.60
     Stoll
    -0.59
     removeFrom
    -0.59
     FANDOM
    -0.59
    POSITIVE LOGITS
     names
    1.38
     NAME
    1.35
     name
    1.31
     Name
    1.27
     Names
    1.27
     getName
    1.17
    names
    1.15
    NAME
    1.13
     newName
    1.10
     setName
    1.10
    Activations Density 0.102%

    No Known Activations