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. 14-GEMMASCOPE-RES-16K
    6. 10478
    Prev
    Next
    INDEX
    Explanations

    phrases containing relative pronouns like "that" and "which"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desorption
    -0.64
     sqlSession
    -0.63
    Nef
    -0.60
    tioned
    -0.58
     käns
    -0.58
     alberi
    -0.57
     scolaires
    -0.54
     skrevet
    -0.51
     spørs
    -0.51
    ual
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.93
    '%(
    0.88
    ]]);
    0.87
     []:
    0.85
    TagMode
    0.84
    %]
    0.83
    )");
    
    0.82
    })();
    
    0.82
    };*/
    0.81
    =")
    0.81
    Activations Density 0.391%

    No Known Activations