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. 6-GEMMASCOPE-RES-16K
    6. 149
    Prev
    Next
    INDEX
    Explanations

    references to specific topics or subjects being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AxisAlignment
    -0.78
    ISupport
    -0.70
    ]--;
    -0.67
     الحره
    -0.67
    makeConstraints
    -0.65
    igshid
    -0.64
    []);
    -0.63
    GIVEREF
    -0.63
    ]),
    
    -0.63
    BRUARY
    -0.63
    POSITIVE LOGITS
    RTEE
    0.58
     fenomeno
    0.57
    matter
    0.56
     matter
    0.56
     concetto
    0.53
    tagHelperRunner
    0.52
     MATTER
    0.48
     issue
    0.47
    atorics
    0.47
     respeito
    0.47
    Activations Density 0.612%

    No Known Activations