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. 25-GEMMASCOPE-RES-16K
    6. 8721
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to licenses and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.56
    BufferException
    -0.53
     tủ
    -0.50
    GOTREF
    -0.50
    yntaxException
    -0.49
     ComVisible
    -0.47
    aronder
    -0.47
     pores
    -0.47
    HasAnnotation
    -0.46
    Notae
    -0.46
    POSITIVE LOGITS
    }
    0.55
    Encyklopedia
    0.53
    }
    
    0.52
    ]='\
    0.51
     coûts
    0.48
    ValueStyle
    0.48
     dalamnya
    0.48
    )}_
    0.47
    ]));
    
    0.47
    lase
    0.47
    Activations Density 0.073%

    No Known Activations