Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6675
    Prev
    Next
    INDEX
    Explanations

    phrases related to hopes and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muñeca
    -0.43
    astéro
    -0.42
    期刊论文
    -0.42
     médicale
    -0.41
     poupée
    -0.40
    endorong
    -0.40
    ække
    -0.39
    انيف
    -0.39
     الرياضيه
    -0.38
    hésite
    -0.38
    POSITIVE LOGITS
     expectations
    1.38
     Expectations
    1.27
    expectations
    1.16
     expectation
    1.16
    Expectations
    1.12
     Expectation
    1.09
    expectation
    1.02
     expectativas
    0.98
    Expectation
    0.94
     hopes
    0.90
    Activations Density 0.409%

    No Known Activations