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. 7-GEMMASCOPE-RES-16K
    6. 4625
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to arrays and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bisk
    -0.63
     CH
    -0.59
    ced
    -0.59
    dfrac
    -0.58
    kun
    -0.57
    เด
    -0.56
     McCa
    -0.56
    ress
    -0.55
    ################
    -0.55
     Völ
    -0.54
    POSITIVE LOGITS
    __":
    
    1.76
    __':
    
    1.74
    )";
    
    1.45
    )");
    
    1.27
    ]";
    1.23
    '])){
    
    1.23
    __":
    1.22
    ]));
    
    1.20
    }>;
    1.20
    ]';
    1.17
    Activations Density 0.457%

    No Known Activations