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. 5-GEMMASCOPE-RES-16K
    6. 15894
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically apostrophes indicating contractions or possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.84
    >"+
    -0.81
    >'+
    -0.80
    })));
    -0.79
    )}+\
    -0.78
    ]]=
    -0.77
    ]+=
    -0.75
    enterOuterAlt
    -0.75
    出版年
    -0.74
    )}-\
    -0.74
    POSITIVE LOGITS
    <bos>
    0.63
    [toxicity=0]
    0.61
    '
    0.61
    ↵↵
    0.55
    I
    0.53
    ה
    0.52
    The
    0.51
    In
    0.50
    стоян
    0.50
    AÇÃO
    0.49
    Activations Density 0.091%

    No Known Activations